A Project Report

On
Enhancing Candidate Experience: An Approach To Optimizing
AI Application Tracking System

Submitted in partial fulfillment of the requirements

for the award of the degree of

Bachelor of Technology
in
Computer Science & Engineering

Submitted By:
Prachi Gupta(2021218943),
Akshat Jain(2021218813),
Liza(2021218908),
Piyush Mittal(2021218940)

Under the Supervision of

Ms. Harshita Samota
[Assistant Professor]

Panipat Institute of Engineering & Technology, Samalkha, Panipat

Affiliated to

Kurukshetra University Kurukshetra, India

(2023-2024)
 An Approach To Optimizing AI Application Tracking System

DECLARATION
We hereby declare that the work presented in this project report entitled “Enhancing Candidate
Experience: An Approach To Optimizing AI Application Tracking System“, in partial fulfillment
of the requirement for the award of the degree of Bachelor of Technology in Computer Science &
Engineering., submitted to Kurukshetra University, Kurukshetra, India is an authentic record of
our own work carried out during the period from Jan 2024 to June 2022 under the guidance of
guide Ms. Harshita Samota with designation. .

We hereby declare that this submission is our own work and that, to the best of our knowledge and
belief, it contains no material previously published or written by another person nor material which
to a substantial extent has been accepted for the award of any other degree or diploma of the
university or other institute of higher learning, except where due acknowledgment has been made
in the text.

Name: Prachi Gupta Name: Akshat Jain

Roll No.: 2021218943 Roll No.: 2021218813

Signature: Signature:

Date: Date:

Name: Liza Name: Piyush Mittal

Roll No.: 2021218908 Roll No.: 2021218940

Signature: Signature:

Date: Date:

Group No 40 Panipat Institute of Engineering and Technology Page 2

 An Approach To Optimizing AI Application Tracking System

Panipat Institute of Engineering &

Technology
70 K.M., G.T. Karnal Road, NH-I, PATTIKALYANA-132 102 Samalkha
(Panipat) Haryana Phone: 0180-3059200, 2569700, 2569599, 2569699, 2569799
Fax: 0180-2569800 Mobile: 09354613020
e-mail: [email protected] website: www.piet.co.in

CERTIFICATE

This is to certify that the Project-I report (PROJ–CS-302A) entitled “Enhancing Candidate
Experience: An Approach To Optimizing AI Application Tracking System“ done by Prachi
Gupta(2021218943), Akshat Jain(2021218813), Liza(2021218908), Piyush Mittal(2021218940)
is an authentic work carried out by them at PIET, Samalkha, Panipat under my guidance. The
matter embodied in this project work has not been submitted earlier for the award of any degree
or diploma to the best of my knowledge and belief.

Dr. Amit Batra

Ms Harshita Samota Mr. Gagan Dua

(Project Guide) (Project Coordinators)

Prof. Dr. S C Gupta

HOD (CSE)

PIET, Samalkha

Group No 40 Panipat Institute of Engineering and Technology Page 3

 An Approach To Optimizing AI Application Tracking System

ACKNOWLEDGEMENT

It gives us a great sense of pleasure to present the report of the B. Tech Project undertaken during
B. Tech. 3rd Year. We owe special debt of gratitude to Assistant Professor Ms. Harshita Samota,
Department of Computer Science & Engineering, PIET, Samalkha for his constant support and
guidance throughout the course of our work. His sincerity, thoroughness and perseverance have
been a constant source of inspiration for us. It is only his cognizant efforts that our endeavors have
seen light of the day.

We also take the opportunity to acknowledge the contribution of Professor Dr. S C Gupta, Head,
Department of Computer Science & Engineering, PIET, Samalkha for his full support and
assistance during the development of the project.

We also do not like to miss the opportunity to acknowledge the contribution of all faculty members
of the department for their kind assistance and cooperation during the development of our project.
Last but not the least, we acknowledge our friends for their contribution in the completion of the
project.

Name: Prachi Gupta Name: Akshat Jain

Roll No.: 2021218943 Roll No.: 2021218813

Signature: Signature:

Date: Date:

Name: Liza Name: Piyush Mittal

Roll No.: 2021218908 Roll No.: 2021218940

Signature: Signature:

Date: Date:

Group No 40 Panipat Institute of Engineering and Technology Page 4

 An Approach To Optimizing AI Application Tracking System

ABSTRACT

“Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking

System“ is a comprehensive tool designed to revolutionize the resume screening process for
organizations, colleges, and individual users alike. By harnessing the latest in parsing techniques
and algorithmic prowess, this tool redefines how resumes are processed, providing a
comprehensive suite of features to elevate the recruitment experience.

On the applicant side, users can easily upload their resumes, allowing the system to extract crucial
information such as basic details, skills, and prowess levels. Leveraging sophisticated algorithms,
the tool offers personalized recommendations, including additional skills to enhance the resume,
suitable job roles, expertise levels, and suggestions for relevant courses and certificates.
Furthermore, applicants receive valuable tips and ideas to optimize their resumes, culminating in
an overall score and access to curated YouTube videos for interview and resume guidance.

Meanwhile, on the admin side, the tool provides a streamlined interface to manage and analyze
applicant data. Administrators can effortlessly view all applicant records in a tabular format,
download data for further analysis in CSV files, and gain insights through intuitive visualizations
like pie-charts depicting predicted roles based on skills and distribution of user experience levels.
Additionally, the tool offers valuable metrics such as the total number of uploaded resumes and a
monthly timeline to track activity.

In crux, “Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking

System“ empowers both applicants and administrators with powerful tools to streamline the
resume screening process, make informed decisions, and ultimately enhance the efficiency of
talent acquisition processes.By leveraging the power of AI-driven insights, it not only streamlines
the resume screening process but also empowers stakeholders to make informed decisions, driving
organizational success and fostering talent growth.

Group No 40 Panipat Institute of Engineering and Technology Page 5

 An Approach To Optimizing AI Application Tracking System

Table of Contents
DECLARATION 2
CERTIFICATE 3
ACKNOWLEDGEMENT 4
ABSTRACT 5

CHAPTER 1: INTRODUCTION 13
1.1 Topic of the System........................................................................................................ 13

1.2 Project Abstract .............................................................................................................. 13

1.3 Purpose of the System .................................................................................................... 13

1.4 Target User ..................................................................................................................... 13

1.5 Topic Background ............................................................................................................ 2

1.6 Problem Context............................................................................................................... 3

1.7 Rationale behind the System: Why do we need this System?.......................................... 3

1.8 Objectives of the System .................................................................................................. 5

1.8.1 Project Objectives ..................................................................................................... 5

1.8.2 Learning Objectives .................................................................................................. 6

1.9 Scope of the System ......................................................................................................... 7

1.10 Limitation of the System .................................................................................................. 7

1.11 Assumptions Made ........................................................................................................... 8

1.12 Success Criteria ................................................................................................................ 8

1.13 Functionalities of the System ........................................................................................... 8

1.13.1 Core Features ............................................................................................................ 9

1.13.2 Enhanced Features .................................................................................................... 9

1.13.3 Special Features ...................................................................................................... 10

1.14 Conclusion...................................................................................................................... 10

CHAPTER 2: PROBLEM DESCRIPTION 11

Group No 40 Panipat Institute of Engineering and Technology Page 6

 An Approach To Optimizing AI Application Tracking System

2.1 Current Problem Description ......................................................................................... 11

2.1.1 Description of Problem Area .................................................................................. 11

2.2 Problem Importance and 24

2.3 Nature of Challenge ....................................................................................................... 12

2.3.1 Domain Challenge .................................................................................................. 12

2.3.2 Technical Challenge................................................................................................ 13

2.4 Feasibility Study............................................................................................................. 14

2.4.1 Technical Feasibility ............................................................................................... 14

2.4.2 Economic Feasibility .............................................................................................. 16

2.4.3 Schedule Feasibility ................................................................................................ 16

2.5 Conclusion...................................................................................................................... 17

CHAPTER 3: LITERATURE REVIEW 18

3.1 Introduction to Literature Review .................................................................................. 18

3.2 Advanced Preliminary Research .................................................................................... 18

3.3 Academic Research ........................................................................................................ 19

3.4 Domain Research ........................................................................................................... 22

3.4.3 Security and Permissions ........................................................................................ 24

3.5 Market Review ............................................................................................................... 24

3.6 Product Analysis ............................................................................................................ 27

3.6.1 Qualitative Analysis ................................................................................................ 27

3.6.2 Quantitative Analysis .............................................................................................. 28

3.7 Critical Evaluation of Market Review ........................................................................... 29

3.8 Conclusion...................................................................................................................... 29

Group No 40 Panipat Institute of Engineering and Technology Page 7

 An Approach To Optimizing AI Application Tracking System

CHAPTER 4: RESEARCH METHODS 31

4.1.1 Primary Research ........................................................................................................ 31

4.1.2 Questionnaire .............................................................................................................. 31

4.1.3 Interview ................................................................................................................. 41

4.2 Secondary Research ....................................................................................................... 43

4.2.1 Technical Research ................................................................................................. 44

4.3 Conclusion...................................................................................................................... 53

CHAPTER 5: ANALYSIS 54

5.1 Questionnaire ................................................................................................................. 54

5.2 Feedback of Questionnaire ............................................................................................. 54

5.1.1 Overall Conclusion of Questionnaire...................................................................... 54

5.2.1 Overall Conclusion of Interview ............................................................................. 54

CHAPTER 6: SYSTEM DESIGN 55

6.1 Introduction .................................................................................................................... 55

6.2 UML Diagram ................................................................................................................ 55

6.2.1 Error! Bookmark not defined.

6.2.2 Sequence DiagramError! Bookmark not defined.

6.2.3 Activity Diagram .................................................................................................... 86

6.3 Entity Relation Model .................................................................................................... 94

6.3.1 List of Entities ......................................................................................................... 95

6.4 Normalization ................................................................................................................. 95

6.4.1 First Normal Form ...................................................................................................... 95

6.4.2 Second Normal Form.................................................................................................. 95

6.4.3 Third Normal Form .................................................................................................... 96

Group No 40 Panipat Institute of Engineering and Technology Page 8

 An Approach To Optimizing AI Application Tracking System

6.5 Sample Resume Uploaded ............................................................................................ 96

CHAPTER 7: IMPLEMENTATION 97

7.1 Introduction .................................................................................................................... 97

7.2 Tools used for Implementation ...................................................................................... 97

7.3 Implementation Plan ...................................................................................................... 98

7.3.1 Implementation Approach ...................................................................................... 98

7.3.1 Implementation Approach Steps ............................................................................. 98

7.4 Traceability of Implementation Modules with Design ................................................ 100

7.5 Implementation of Complex Modules.......................................................................... 100

7.6 Technical Quality and Other Features .......................................................................... 104

7.6.1 Memory Utilization ............................................................................................... 104

7.6.2 Performance .......................................................................................................... 105

7.6.3 User Interface ........................................................................................................ 105

7.6.4 Naming Conventions ............................................................................................ 105

7.6.5 Comments ............................................................................................................. 107

7.7 User Manual ................................................................................................................. 107

7.8 Technical Manual ......................................................................................................... 114

CHAPTER 8: TESTING 118

8.1 Introduction .................................................................................................................. 118

8.2 Need of Testing ............................................................................................................ 118

8.3 Test Plan ....................................................................................................................... 118

8.3.1 Type of Testing ......................................................................................................... 119

8.3.2 Pass/Fail Criteria....................................................................................................... 121

8.4 Point of Contact of Troubleshooting Purpose .............................................................. 121

Group No 40 Panipat Institute of Engineering and Technology Page 9

 An Approach To Optimizing AI Application Tracking System

8.5 Testing Duration ........................................................................................................... 121

8.6 Criteria of Test Cases ................................................................................................... 121

8.7 Technical requirements for Testing.............................................................................. 122

8.8 Users Involved in Testing ............................................................................................ 122

8.9 Unit Testing .................................................................................................................. 122

8.9.1 Justification for unit Testing ................................................................................. 122

8.9.2 Black box testing (Functional Testing) ................................................................. 123

8.9.3 White Box Testing (Conceptual Testing) ............................................................. 135

8.10 Integration Testing ....................................................................................................... 144

8.10. Technique used for Integration Testing ................................................................ 144

8.10.2 Justification for Integration Testing ...................................................................... 144

8.11 System Testing ............................................................................................................. 146

8.12 Compatibility Testing................................................................................................... 149

8.13 GUI Testing .................................................................................................................. 151

8.14 Usability Testing and its Justification .......................................................................... 152

8.14.1 User Acceptance Testing (UAT) .............................................................................. 154

8.14.2 Justification for User Acceptance Testing ............................................................ 154

8.15 Conclusion.................................................................................................................... 157

CHAPTER 9: CRITICAL EVALUATION 159

9.1 Critical Evaluation............................................................................................................. 159

9.2. Factors of Benefit (Usefulness of System to Target Audience) ....................................... 159

9.3 Comparison with Other Systems .................................................................................. 160

9.3.1 Success Assessment ............................................................................................. 160

9.3.2 Critical Appraisal .................................................................................................. 162

Group No 40 Panipat Institute of Engineering and Technology Page 10

 An Approach To Optimizing AI Application Tracking System

CHAPTER 10: CONCLUSION 163

10.1 Success Criteria ............................................................................................................ 163

10.2 Limitations and Errors in the Developed System: ....................................................... 163

10.3 Future Enhancement ..................................................................................................... 163

10.4 What would have been done if given time to redo the project? ................................... 163

10.5 Computational Challenges ........................................................................................... 164

10.6 Learning Experience Gathered ..................................................................................... 164

10.6 Conclusion.................................................................................................................... 165

CHAPTER 11: REFERENCES 168

11.1 Books............................................................................................................................ 168

11.2 Journals......................................................................................................................... 169

11.3 Websites ....................................................................................................................... 169

APPENDIX 171

Group No 40 Panipat Institute of Engineering and Technology Page 11

 An Approach To Optimizing AI Application Tracking System

CHAPTER 1: INTRODUCTION
1.1 Topic of the System
Title: - “Enhancing Candidate Experience: An Approach To Optimizing AI Application
Tracking System”

1.2 Project Abstract

"Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" revolutionizes resume screening with advanced parsing and algorithmic analysis.
Applicants upload resumes for detailed surveys, receiving personalized recommendations on
skills, job roles, and certifications. Tips and insights buoy up resume quality, while an overall score
and curated YouTube resources aid interview preparation. Administrators access applicant data in
tabular form, downloadable for further analysis. Visualizations offer vision on predicted roles and
experience levels. Key metrics track activity trends. This innovative tool bridges applicant-
recruiter gaps, enhancing recruitment efficiency and decision-making.

1.3 Purpose of the System

The purpose of the "Enhancing Candidate Experience: An Approach To Optimizing AI
Application Tracking System" project is to recast resume screening by leveraging advanced
parsing techniques and algorithms. It aims to provide applicants with personalized
recommendations for skill enhancement, job role suitability, and relevant certifications.
Additionally, it authorizes the applicants with valuable insights, vision and tips to optimize their
resumes and improve interview readiness. Administratively, the project offers a streamlined
interface for coherent management of applicant data, providing visualizations and key metrics to
track recruitment trends. Ultimately, the project seeks to bridge the gap between applicants and
recruiters, enhancing the efficiency and effectiveness of the recruitment process.

Group No 40 Panipat Institute of Engineering and Technology Page 13

 An Approach To Optimizing AI Application Tracking System

1.4 Target User

The "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" project targets a diverse range of users involved in the recruitment process:
1. Organizations: Companies of all sizes across various industries can utilize the tool to
streamline their recruitment processes, ensuring efficient screening of resumes and better
selection of candidates.
2. Colleges and Universities: Educational institutions can benefit from the tool to facilitate
career services for students and alumni, assisting them in optimizing their resumes for job
applications and career advancement.
3. Recruitment Agencies: Agencies specializing in talent acquisition can leverage the tool
to enhance their efficiency in matching candidates with suitable job opportunities,
improving client satisfaction and retention.
4. Individual Users: Job seekers can use the tool to refine their resumes, receive personalized
recommendations, and improve their chances of landing interviews and securing
employment opportunities.
Overall, the project caters to a wide spectrum of users, aiming to provide high value and efficiency
at every stage of the process.

1.5 Topic Background

The topic of resume parsing and analysis within the realm of artificial intelligence, technology has
gained significant resistance in recent years. With the increasing volume of job applications and
the need for efficient talent acquisition processes, organizations are turning to innovative solutions
like the "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" project to streamline their hiring efforts.
Traditional methods of resume screening often involve manual review processes that are time-
consuming and vulnerable to human error. However, advancements in natural language processing
(NLP) and machine learning have paved the way for automated resume parsing tools that can
extract relevant information from resumes, such as skills, qualifications, and experience, in a
structured format.

Group No 40 Panipat Institute of Engineering and Technology Page 14

 An Approach To Optimizing AI Application Tracking System

Moreover, AI-driven algorithms can analyze this structured data to provide insights and
recommendations to both applicants and recruiters. For applicants, these visions may include
suggestions for improving their resumes or recommendations for relevant job opportunities. On
the other hand, recruiters can benefit from tools that offer data visualization capabilities, allowing
them to quickly identify top candidates or trends in applicant pools.
Overall, the "Enhancing Candidate Experience: An Approach To Optimizing AI Application
Tracking System" project aligns with the broader trend of leveraging AI and machine learning
technologies to optimize recruitment processes, improve decision-making, and enhance the overall
candidate experience. As organizations continue to prioritize efficiency and effectiveness in talent
acquisition, projects like these play a vital role in shaping the future of recruitment.

1.6 Problem Context

Traditional resume screening is slow and error-prone. As job applications surge, organizations face
difficulty in efficiently identifying qualified candidates due to varied resume formats and
subjective evaluation. Automating this process with AI-driven parsing tools becomes essential to
streamline hiring by extracting key information and providing actionable insights.

1.7 Rationale behind the System: Why do we need this System?

The rationale behind the "Enhancing Candidate Experience: An Approach To Optimizing AI
Application Tracking System" system stems from the inefficiencies and challenges inherent in
traditional resume screening processes. Manual resume screening is time-consuming, prone to
errors, and often lacks standardization. This system aims to automate and optimize the resume
screening process, saving time, improving accuracy, and enhancing the overall effectiveness of
talent acquisition efforts.

1.7.1 Benefits of the System: What are the potential benefits derived?
The "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" system offers several benefits:
1. Efficiency and accuracy: Automating the resume screening process saves time and
resources by swiftly parsing and analyzing large volumes of resumes, enabling recruiters

Group No 40 Panipat Institute of Engineering and Technology Page 15

 An Approach To Optimizing AI Application Tracking System

to focus on more strategic tasks. By utilizing advanced parsing techniques and algorithms,
the system ensures consistent and objective evaluation of resumes, minimizing human error
and bias in the screening process.
2. Enhanced Candidate Experience: Applicants receive personalized recommendations and
insights to improve their resumes, enhancing their chances of success in job applications
and interviews.
3. Improved Recruitment Decisions: Recruiters gain access to structured insights and
visualizations, enabling them to make data-driven decisions, identify top candidates more
efficiently, and match them to suitable job roles.
4. Standardization: The system promotes standardization in resume evaluation by extracting
key information in a structured format, facilitating fair and consistent screening practices
across different applicants and positions.
5. Cost Savings: By streamlining the recruitment process and reducing manual effort, the
system helps organizations save costs associated with hiring, such as labor expenses and
time-to-fill metrics.
Overall, the system drives efficiency, accuracy, and fairness in the recruitment process, ultimately
leading to better hiring decisions and improved organizational outcomes.
1.8 Objectives of the System
1.8.1 Project Objectives
⮲ Automated Resume Parsing: Developing a system capable of parsing unstructured
resume data into structured formats, extracting key information such as basic details, skills,
and experience levels.
⮲ Algorithmic Analysis: Implementing algorithms to analyze parsed resume data, providing
personalized recommendations for skill enhancement, job role suitability, and relevant
certifications.

⮲ User-Friendly Interface: Designing an intuitive interface for applicants to upload resumes

and receive insights, and for administrators to manage applicant data efficiently.

Group No 40 Panipat Institute of Engineering and Technology Page 16

 An Approach To Optimizing AI Application Tracking System

⮲ Data Storage and Analysis: Establishing a database to store parsed resume data and
generate insights, enabling administrators to track recruitment trends and make informed
decisions.

⮲ Scalability and Adaptability: Ensuring the system is scalable to accommodate varying

volumes of resumes and adaptable to evolving recruitment needs, supporting future
enhancements and feature additions.

1.8.2 Learning Objectives

⮲ Technical Skills: Gain proficiency in natural language processing (NLP) techniques,
machine learning algorithms, and database management for developing the resume parsing
and analysis system.
⮲ User Experience Design: Acquire skills in user interface (UI) and user experience (UX)
design principles to create an intuitive and user-friendly interface for both applicants and
administrators.
⮲ Data Management: Learn database management skills to effectively store, retrieve, and
analyze large volumes of resume data, enabling informed decision-making and trend
analysis.
⮲ Algorithm Development: Develop expertise in designing and implementing algorithms
for analyzing resume data, including recommendation systems for skill enhancement and
job role suitability.

⮲ Project Management: Gain experience in project planning, execution, and iteration,

including requirements gathering, design, development, testing, and deployment of the
resume parsing and analysis system.

1.9 Scope of the System

The scope of the "Resume AI Analyzer" system includes parsing and analyzing resumes, providing
personalized recommendations, offering a user-friendly interface, managing a secure database,
developing algorithms for analysis, visualizing data insights, ensuring security and compliance,
and integrating with existing workflows while allowing scalability for future enhancements.

Group No 40 Panipat Institute of Engineering and Technology Page 17

 An Approach To Optimizing AI Application Tracking System

1.10 Limitation of the System

While the "Resume AI Analyzer" system offers numerous benefits, it also has some limitations:
1. Language and Format Constraints: The system may face challenges in parsing resumes
written in languages other than the primary language it supports, as well as resumes with
unconventional formats or layouts.
2. Accuracy of Parsing: Despite advancements in natural language processing, the system
may not always accurately parse and extract information from resumes, leading to errors
or omissions in the structured data.
3. Bias in Algorithms: The recommendations and insights provided by the system may be
influenced by inherent biases present in the algorithms, potentially resulting in skewed or
unfair outcomes, particularly in sensitive areas such as job role suitability.
4. Limited Data Sources: The effectiveness of the system relies on the availability and
quality of data sources for training algorithms and generating insights. Limited access to
diverse and representative resume datasets may impact the system's performance and
generalizability.
5. Privacy and Security Concerns: Storing and processing sensitive personal information
from resumes raises privacy and security concerns. Ensuring compliance with data
protection regulations and safeguarding against unauthorized access or data breaches is
crucial.
6. Dependency on Technology: The system's functionality is dependent on the reliability and
availability of technology infrastructure, including servers, databases, and internet
connectivity. Downtime or technical issues may disrupt system operations and impact user
experience.
7. Lack of Human Judgment: Automated parsing and analysis may lack the nuanced
judgment and contextual understanding that human recruiters possess, potentially
overlooking relevant details or misinterpreting information in resumes.
Addressing these limitations requires ongoing refinement and improvement of the system, as well
as careful consideration of ethical and regulatory implications in resume processing and analysis.

Group No 40 Panipat Institute of Engineering and Technology Page 18

 An Approach To Optimizing AI Application Tracking System

1.11 Assumptions Made

This system is although easy to use in terms of its functionalities but even then, there are some
assumptions that need to be made before the development of the system:

⮲ Users need to have basic knowledge of using android phones

⮲ Good knowledge of English and basics of Internet is required, i.e. user needs to be a
computer literate.
⮲ The smartphone users have not yet encountered any secure solution to protect their data
from being stolen or mishandled
⮲ The user who would be using the app, is expected to have a smartphone with a good quality
front camera.

1.12 Success Criteria

The success of the system will be measured by its ability to efficiently parse and analyze
resumes. How efficiently the system provides accurate and relevant recommendations
based on enhancing the user experience through a user-friendly interface. The system;s
success criteria also ensures data security and seamlessly integrates with existing
workflows while enabling scalability for future needs.
1.13 Functionalities of the System
The proposed system having some core, enhanced and some special functionality. So, let’s know
them one by one and use of this functionality in this system.

Group No 40 Panipat Institute of Engineering and Technology Page 19

 An Approach To Optimizing AI Application Tracking System

1.13.1 Core Features

Functionality Description

Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking

System Using QR Code
Utilizing natural language processing (NLP) techniques to
extract structured data from unstructured resume documents.
Resume Parsing
This involves identifying and categorizing information such as
contact details, work experience, education, and skills..
Identifying relevant keywords and phrases within the parsed
resume data to highlight key skills, experiences, and
Keywords Extraction:
qualifications. This helps recruiters quickly assess the
suitability of candidates for specific roles.
Table 3: Core Feature

1.13.2 Enhanced Features

Functionality Description

Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking

System Using QR Code
Implementing entity recognition algorithms to identify and
extract specific entities such as names, addresses, and
Entity Recognition educational institutions mentioned within the resumes. This
facilitates further analysis and enhances the accuracy of
extracted information.
Employing sentiment analysis techniques to evaluate the
sentiment of text segments within the resumes. This allows for
Sentiment Analysis
the assessment of candidate enthusiasm, positivity, and overall
attitude, providing additional insights for recruiters.
Table 4: Enhanced Features

Group No 40 Panipat Institute of Engineering and Technology Page 20

 An Approach To Optimizing AI Application Tracking System

1.13.3 Special Features

Functionality Description

Enhancing Candidate Experience: An Approach To Optimizing AI Application

Tracking System Using QR Code
Developing machine learning classifiers to match resumes
with job descriptions based on similarity scores. By analyzing
Job Matching the content of both resumes and job postings, the system can
recommend the most suitable candidates for specific roles,
improving recruitment efficiency.
Creating a user-friendly interface for uploading, analyzing,
and visualizing resume data. This interface will be intuitive
User Interface
and accessible, allowing applicants to easily upload their
resumes and recruiters to efficiently review and interact with
the parsed data, enhancing the overall user experience.
Table 5: Special Features

Group No 40 Panipat Institute of Engineering and Technology Page 21

 An Approach To Optimizing AI Application Tracking System

1.14 Conclusion
In conclusion, the "Enhancing Candidate Experience: An Approach To Optimizing AI
Application Tracking System" system represents a transformative solution in the domain of
recruitment technology, addressing the inefficiencies and challenges intrinsic in traditional resume
screening processes. By exploiting advanced parsing techniques and algorithms and AI-driven
insights, the system streamlines resume analysis, enhances decision-making, and improves the
overall recruitment experience for both applicants and recruiters. With its core features enabling
accurate parsing and keyword extraction, enhanced functionalities facilitating entity recognition
and sentiment analysis, and special features such as job matching and user-friendly interface, the
system empowers organizations to make informed hiring decisions efficiently and effectively in
today's competitive job market.

Group No 40 Panipat Institute of Engineering and Technology Page 22

 An Approach To Optimizing AI Application Tracking System

CHAPTER 2: PROBLEM DESCRIPTION

2.1 Current Problem Description

After the analysis of preliminary investigation, the researcher has spotted and identified some of
the main problem areas of the application which are briefly described below:

2.1.1 Description of Problem Area

While the "Enhancing Candidate Experience: An Approach To Optimizing AI Application

Tracking System" system offers significant benefits, there are several potential problem areas that
warrant attention:

1. Data Accuracy and Integrity: The system's effectiveness majorly relies on the accuracy
and integrity of the parsed resume data. Inaccurate parsing or misinterpretation of
information and data could lead to flawed recommendations and incorrect decision-
making.
2. Privacy and Security Concerns: Storing and processing sensitive personal information
from resumes raises privacy and security concerns. Ensuring compliance with data
protection regulations and implementing robust security measures is essential to safeguard
applicant data.
3. Bias in Algorithms: There is a risk of bias in the algorithms used for resume parsing and
analysis, which could result in unfair treatment of certain candidates based on factors such
as gender, race, or background.
4. Integration Challenges: Integrating the system with existing recruitment workflows and
systems may present challenges, especially if compatibility issues arise or if the integration
process is complex and time-consuming.
5. User Experience: The system's user interface plays a crucial role in its adoption and
effectiveness. Poorly designed interfaces could hinder user engagement and satisfaction.

Group No 40 Panipat Institute of Engineering and Technology Page 23

 An Approach To Optimizing AI Application Tracking System

6. Scalability and Performance: As the volume of resume data grows, the system must be
able to scale effectively to handle increasing demands without sacrificing performance.
Scalability issues could lead to delays in processing and analysis.
7. Ethical Considerations: Ethical considerations surrounding the use of AI in recruitment,
such as transparency, fairness, and accountability, must be carefully addressed to ensure
ethical and responsible use of the system.

2.2 Problem Importance and Proposed Solution

The solution for the current system is to develop a system which will sort out all the above
problems. The proposed system will work upon the current issues and will overcome the problem
that it has right now:

1. Data Accuracy and Integrity: Implementing rigorous testing and validation processes for
parsing algorithms. Continuously refining the algorithms based on feedback and
performance metrics. Incorporating the different mechanisms for error correction and data
validation to ensure the accuracy of the system is used.
2. Privacy and Security Concerns: Implementing encryption and access controls to protect
sensitive data to comply with data protection regulations and industry standards.
Conducting regular security checks and penetration testing to identify varied vulnerabilities
in the system. Training the staff on data security best practices.
3. Bias in Algorithms: Conducting bias audits to identify and mitigate algorithmic biases.
Using diverse and representative training data to reduce biases. Implementing fairness
metrics and algorithms that promote equitable outcomes. Providing transparency in
algorithmic decision-making to increase trust.
4. Integration Challenges: Collaborating closely with stakeholders to understand integration
requirements and address compatibility issues and providing comprehensive
documentation and support for integration. Implementation of the standardized data
formats and APIs to facilitate seamless integration with existing systems.

Group No 40 Panipat Institute of Engineering and Technology Page 24

 An Approach To Optimizing AI Application Tracking System

5. User Experience: Conduction of user testing and gathering feedback to improve the user
interface and prioritizing simplicity and intuitiveness in design. Providing clear
instructions and guidance to users. Offer training and support resources to help users
navigate the system effectively.
6. Scalability and Performance: Architect the system for scalability by using cloud-based
infrastructure and distributed computing technologies. Optimize algorithms and processing
pipelines for efficiency. Monitoring the system performance and scalability metrics, and
adjust resources as needed.
7. Ethical Considerations: Establishing ethical guidelines and governance mechanisms for
AI development and deployment. Conducting the regular audits to assess compliance with
ethical standards. Involve diverse stakeholders in ethical reviews and decision-making
processes.

2.4 Nature of Challenge

2.4.1 Domain Challenge
To build this app, the researcher would have to undergo some major challenges during the
development like:

1. Variability in Resume Formats: Resumes can vary widely in format, layout, and
structure, making it challenging to create robust parsing algorithms that can accurately
extract information from diverse document styles.
2. Data Privacy and Compliance: Compliance with data privacy regulations, such as GDPR
or HIPAA, presents challenges in handling sensitive personal information contained within
resumes while ensuring confidentiality, data security, and compliance with legal
requirements.
3. Ambiguity in Language: Resumes often contain ambiguous language, abbreviations, and
industry-specific jargon, which can pose challenges for natural language processing
algorithms in accurately interpreting and extracting relevant information.
4. Algorithmic Bias and Fairness: Addressing biases in algorithmic decision-making and
ensuring fairness in recommendations and analysis is crucial to avoid perpetuating

Group No 40 Panipat Institute of Engineering and Technology Page 25

 An Approach To Optimizing AI Application Tracking System

inequalities or discriminatory outcomes based on factors such as gender, race, or

background.
5. Handling Multilingual Resumes: The system may need to support parsing and analysis
of resumes written in multiple languages, requiring robust language detection and
translation capabilities to ensure accuracy and consistency across different language
contexts.
6. Scalability and Performance: As the volume of resume data grows, the system must be
able to scale effectively to handle increasing loads without sacrificing performance. This
requires careful design and optimization of algorithms, infrastructure, and processing
pipelines to ensure responsiveness and efficiency.
7. Integration with Existing Systems: Integrating the system with existing recruitment
workflows, applicant tracking systems, and HR databases may present challenges in
compatibility, data migration, and interoperability, requiring close collaboration with
stakeholders and adherence to industry standards.
8. User Adoption and Training: Ensuring user adoption and providing adequate training
and support for recruiters, HR professionals, and applicants to effectively use the system
requires attention to user experience design, usability testing, and comprehensive training
resources.

These domain-specific challenges require a deep understanding of the recruitment domain,

collaboration with domain experts, continuous feedback and iteration, and a commitment to
excellence in system design and development.

2.4.2 Technical Challenge

The challenges that would come on the way of the researcher while working on the technology
area. In addition to domain-specific challenges, the development of the "Enhancing Candidate
Experience: An Approach To Optimizing AI Application Tracking System" system may
encounter several technical challenges:

1. Natural Language Processing (NLP) Complexity: Developing robust NLP algorithms to

accurately parse and extract information from unstructured resume text is challenging due

Group No 40 Panipat Institute of Engineering and Technology Page 26

 An Approach To Optimizing AI Application Tracking System

to the complexity of human language, including grammar variations, synonyms, and

context-dependent meanings.
2. Algorithmic Accuracy and Precision: Ensuring the accuracy and precision of parsing and
analysis algorithms requires rigorous testing and validation against diverse datasets, as well
as fine-tuning parameters to minimize errors and optimize performance.
3. Machine Learning Model Training: Developing machine learning models for tasks such
as job matching or sentiment analysis requires large annotated datasets, expertise in model
selection and tuning, and careful evaluation to ensure generalization and robust
performance.
4. Entity Recognition and Disambiguation: Identifying and disambiguating entities such as
names, addresses, and educational institutions within resume text can be challenging due
to variations in formatting, abbreviations, and homonyms.
5. Sentiment Analysis Complexity: Evaluating the sentiment of text segments within
resumes accurately requires sophisticated sentiment analysis techniques capable of
handling nuances in language and context, such as sarcasm, irony, and subjectivity.
6. Integration with Third-Party Systems: Integrating the system with existing recruitment
platforms, APIs, and databases may involve technical challenges related to data
interoperability, API versioning, authentication, and data synchronization.
7. Scalability and Performance Optimization: Architecting the system for scalability and
optimizing performance to handle large volumes of resume data efficiently requires careful
consideration of factors such as distributed computing, parallel processing, and caching
strategies.
8. Data Privacy and Security: Implementation of robust data privacy and security measures
to protect sensitive personal information within resumes, such as encryption, access
controls, and compliance with regulatory requirements, presents technical challenges in
system design and implementation.

These technical challenges require expertise in natural language processing, machine learning,
software architecture, scalability, security, and data engineering, as well as a commitment to
continuous learning and innovation in technology.

Group No 40 Panipat Institute of Engineering and Technology Page 27

 An Approach To Optimizing AI Application Tracking System

2.5 Feasibility Study

Feasibility study is an analysis and evaluation of a proposed project to determine if it is feasible
technically, economically, timely and operationally. Feasibility study for the project is conducted
to analyze whether the proposed project is possible/ feasible to be developed within scheduled
time, available resources, within estimated budget. After the feasibility study is done, it is
evaluated whether to proceed with the project or not. The feasibility study can be categorized into
following two parts:

1. Technically feasibility
2. Economic feasibility

2.5.1 Technical Feasibility

Technical feasibility is conducted to verify whether the project is feasible to be developed within
the available resources or not. The technical feasibility takes into account the technical
requirements for the project, the technical resources required by the project for its successful and
efficient completion. The specific technical resources to be available for completing the project
successfully are given below:

Hardware Resources
With an Intel Core i5 processor and 8GB of RAM, any computer system should be capable of
handling tasks such as resume parsing, algorithmic analysis, and data visualization efficiently.The
multi-core capabilities of the Intel Core i5 processor will help with parallel processing tasks, which
are common in AI and machine learning algorithms. Additionally, the 8GB of RAM provides
ample memory for running the system and storing intermediate data during processing.

S. No. Hardware Resources

1. Intel(R) Core(TM) i5-5200U CPU @ 2.20GHz 2.19 GHz

2. RAM (Memory) - 8 GB and more

Group No 40 Panipat Institute of Engineering and Technology Page 28

 An Approach To Optimizing AI Application Tracking System

3. Monitor – Any standard monitor

4. Pen Drive, Mouse, Printer, Keyboard

5. System Type- 64-bit operating system, x64-based processor

6. Hard Drive– More than 80 GB

7. Accessories – Internet connection.

Since the computer system is a 64-bit operating system, it takes advantage of the increased memory
address space and better performance for memory-intensive tasks. This is particularly beneficial
for handling large volumes of resume data and complex algorithms.
Overall hardware configuration should be well-suited for running the "Enhancing Candidate
Experience: An Approach To Optimizing AI Application Tracking System" system, but factors
such as storage space and graphics capabilities can be taken into consideration depending upon the
specific requirements of the system and any additional software components the programmer plans
to use.

Software Resources
S. No. Software Resources
1. Visual Studio

2. Database Technology –MySQL

3. Language Used - Python

4. Packages Used - pandas, numpy, pyresparser

5. Documentation and Presentation tool - Microsoft Office 2010

Table 7: Software Resources

2.5.2 Economic Feasibility
The main purpose of conducting economic feasibility is to identify the financial benefits and costs
associated with the project development. As for any system, if the estimated benefits equal or
surpass the expected costs that are calculated for the system then the project would be

Group No 40 Panipat Institute of Engineering and Technology Page 29

 An Approach To Optimizing AI Application Tracking System

economically feasible. Since the proposed system programming environment is based on android
which is an open source platform, there is less of investment in the development portion. And any
software or program that is produced needs to be tested which can be done without much
investment. Only required investment would be a physical device to test the system.

2.5.5 Conclusion of Feasibility Study

The project is technically feasible since the hardware, software and the resources needed for
executing the system are ready. After evaluating the cost and benefits incurred on and derived from
the system, it is concluded that the project is economically feasible.

2.6 Conclusion
In conclusion, while the development of the system despite domain-specific challenges like
variability in resume formats and technical hurdles such as NLP complexity, viable solutions exist.
Continuous testing, algorithm refinement, and data security measures mitigate domain-specific
concerns. Technical challenges are addressed through advanced NLP techniques, optimization for
scalability, and seamless integration. With MySQL, Python 3, Streamlit, and relevant packages,
the "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" system is feasible, promising streamlined recruitment processes and enhanced decision-
making for both applicants and recruiters.

Group No 40 Panipat Institute of Engineering and Technology Page 30

 An Approach To Optimizing AI Application Tracking System

CHAPTER 3: LITERATURE REVIEW

Creating a literature review for the "Enhancing Candidate Experience: An Approach To
Optimizing AI Application Tracking System" system involves examining existing research,
articles, and resources relevant to the project. Here's a general outline incorporating qualitative,
quantitative, and product analysis aspects:

3.1 Introduction to Literature Review

Define Natural Language Processing (NLP) and its applications in text analysis, including resume
parsing and skill extraction. Provide an overview of existing resume analysis methods, including
manual screening, keyword matching, and machine learning approaches. It is conducted using
published books, journals and other research papers and is a baseline for present research. The
following are the purpose of a literature review:

⮲ To perform critical evaluation of already conducted research to find out their ideas, strength,
weakness and their methodologies.
⮲ To have an overview of already existing suggestions related to the subject, review the findings
and views of others.
⮲ To answer certain questions and remove confusions related to the present topic.
3.2 Advanced Preliminary Research
The idea came to the mind of developer while going through the railway station to get the general
ticket with the counter after standing in long queue which is the offline mode. Developer has seen
that due to this long queue or we can say that due to less counter some of the people who are in
hurry to pick his train he/she didn’t able to get the ticket only due to the long queue and the less
counter and due to this it is directly effect to the revenue of the railway. Then the developer has
crack the idea in his mind why not we do this in online mode, as we know that the irctc website
for railway which booked the reserved ticket only but developer think that why it is not possible
that we can book the general ticket in online to solve these problems which are facing by the
general user and it is also directly beneficial to the revenue of the railway people get more ticket
no any problem to stand in queue and it’s also save the time of the people.

As we also know that we are in that era where android mobile is the common for every user. If we
take the hundred people 95% of the people having own smartphone in his hand so why not, we

Group No 40 Panipat Institute of Engineering and Technology Page 31

 An Approach To Optimizing AI Application Tracking System

develop the system in android mobile. There are a lot of application like UTS (Unreserved
Ticketing System), IRCTC Rail info etc. which show the list of the general train, fare of every
train but none of them can book the ticket for the general travelling purpose. In the last year april
2015 irctc has launched the one application which is UTS (Unreserved Ticketing System) which I
want to develop but the main drawback of that system is it just book the ticket for only some select
cities like Delhi, Mumbai, Calcutta etc. but some who wants to travel in the general from Delhi to
Panipat this app is useless so for that these users have to go in offline mode i.e. counter based
ticket. So, developer wants to develop the application like irctc but only for the general as well as
for the platform ticket and stored the user information at the time of registration in the database
for the security purpose and also developer want to gives the facility to the user to the balance
through his e-wallet which is time saving process more in compare to online transaction some time
it being with friend or family transaction process is lost. Also, developer wants to give the ticket
to the users in the form of QR code which is more better way in compare to printed ticket. It that
QR code is has scan by the TTEs where the all the user information is stored in the database and
it also show that the ticket is valid or not. These all the thing which developer think that it is totally
new because none of the system exists in now days so in future it may be possible that it is directly
useful and implemented by the irctc.

3.3 Academic Research

Before developing the proposed system, the developer conducted academic research by reading
research papers, journals etc. to understand the real need of general ticketing application for the
general users and its advantages.how it will be useful to the users. It will also help the developer
to refine the functionalities to be included in the system.

3.4 Domain Research

Domain research is necessary as the project domain varies in various cases and once this is finished
for a particular module, then we can work on analysis and designing of that particular module
provides ease of its use. During the stages of research, the researcher acknowledged that there are
enough problems faced by the user in environment of getting ticket.

Group No 40 Panipat Institute of Engineering and Technology Page 32

 An Approach To Optimizing AI Application Tracking System

The application’s domain area is focused on android based application and mobile computing. To
have a deep knowledge of user requirements and important aspects of the system, researcher has
to implement the technology to reduce problems faced by the user at the time of getting ticket.

3.4.1 Security and Permissions

Every Android application runs its own process and security among which these applications are
applied with the help of Linux installations. Android has a safety mechanism that restricts
processes to perform various operations. Based on the permissions a process can access data from
other applications or other operations. This concept will help developer to maintain the security of
the application and get access to all the permissions for the application. For example, developer
can specify access to the Bluetooth function of the device by the application.

3.5 Market Review

Conducting a market review for the system involves analyzing the current landscape of resume
parsing tools, NLP-based recruitment solutions, and related products in the market. Here's a
structured approach:
1.Identify Competitors:
Research and compile a list of companies offering resume parsing and analysis tools, NLP-based
recruitment platforms, and AI-driven HR software.
Consider both established players and emerging startups in the market.
2.Evaluate Product Offerings:
Review the features, functionalities, and pricing models of competing products.
Assess strengths and weaknesses, including ease of use, accuracy, scalability, integration
capabilities, and customer support.
3. Analyze Market Trends:
Identify key trends and developments in the resume parsing and NLP-based recruitment software
market.
Consider factors such as the adoption of AI and machine learning, increasing demand for
automation in HR processes, and emerging technologies.
4. Assess Target Market Segments:

Group No 40 Panipat Institute of Engineering and Technology Page 33

 An Approach To Optimizing AI Application Tracking System

Define target market segments for the system, such as small businesses, mid-sized enterprises, or
specific industries. Analyze market size, growth potential, and competition within each segment.
5.Customer Feedback and Reviews:
Gather insights from customer reviews, testimonials, and case studies of competing products.
Identify common pain points, user preferences, and areas for improvement based on customer
feedback.
6. Regulatory Environment:
Consider regulatory requirements and compliance standards relevant to HR software and data
privacy (e.g., GDPR, CCPA).
Ensure that the "Resume AI Analyzer" system adheres to legal and ethical guidelines.
7. Partnerships and Integration:
Explore partnerships with complementary HR software providers, job boards, and recruitment
platforms to enhance the value proposition of the system.
Assess integration capabilities and compatibility with existing HR systems and workflows.
8. Market Entry Strategy:
Develop a market entry strategy based on the competitive landscape, target market segments, and
differentiation factors of the system.
Consider pricing strategies, promotional tactics, and sales channels to effectively penetrate the
market.
By conducting a thorough market review, you can gain insights into market dynamics, competitive
positioning, and opportunities for differentiation, helping to inform the marketing, sales, and
product development strategies for the system.

3.6 Product Analysis

Evaluate existing resume analyzer products and tools available in the market, considering factors
such as feature set, ease of use, scalability, and integration capabilities.
Conduct a comparative analysis of product reviews, customer ratings, and user testimonials to
identify strengths and weaknesses of competing solutions.

Group No 40 Panipat Institute of Engineering and Technology Page 34

 An Approach To Optimizing AI Application Tracking System

Highlight key features and functionalities desired by users, such as customizable recommendation
algorithms, real-time feedback mechanisms, and seamless integration with applicant tracking
systems.
3.6.1 Qualitative Analysis
Review qualitative studies and articles on resume analysis techniques, focusing on the challenges
faced by recruiters and the limitations of traditional methods.
Explore research on NLP algorithms, sentiment analysis, and entity recognition in the context of
resume parsing.
Discuss the importance of context, semantics, and user feedback in improving the accuracy and
relevance of resume recommendations.

3.6.2 Quantitative Analysis

Examine quantitative studies evaluating the performance of NLP-based resume analyzers in terms
of accuracy, efficiency, and user satisfaction.
Compare metrics such as precision, recall, and F1 score for different NLP models and techniques.
Analyze user engagement metrics, such as upload rates, recommendation adoption rates, and user
feedback scores, to assess system effectiveness.

3.7 Critical Evaluation of Literature Review

The development of the proposed App for user is researched upon so as to come to the conclusion
what all features are required by the end user to enhance the online ticket booking environment.
The literature review creates the groundwork to carry out further research giving an idea about the
proposed system. The systems similar to the proposed system have been researched upon to create
a base line for the system; what problems the developer can face, what are the features that cannot
be implemented at all.

While reviewing the literature, domain, technical and academic research have been carried out to
get the in-depth knowledge of the features to be implemented in the proposed system and to explore
the technology to be used in implementing the system. Therefore, secondary research is done under
literature review by studying other’s work which will guide the developer towards developing the
proposed system.
Group No 40 Panipat Institute of Engineering and Technology Page 35
 An Approach To Optimizing AI Application Tracking System

3.8 Critical Evaluation of Market Review

Critical evaluation of the market review for the system involves assessing the strengths,
weaknesses, and implications of the findings. Here's a structured approach:
1.Comprehensiveness of Research:
Evaluate the depth and breadth of the market research conducted, considering the range of
competitors analyzed, market segments explored, and sources of information utilized.
Assess whether the research provides a comprehensive understanding of the competitive landscape
and market trends.
2.Accuracy of Data and Analysis:
Scrutinize the accuracy and reliability of data sources used for the market review, including
customer testimonials, industry reports, and market research studies.
Verify the credibility of findings and ensure that conclusions are supported by evidence and
analysis.
3.Relevance of Findings:
Consider the relevance of the market review findings to the objectives and target market of the
"Resume AI Analyzer" system.
Assess whether the identified market trends, customer preferences, and competitive dynamics
align with the system's value proposition and differentiation factors.
4. Identification of Opportunities and Threats:
Evaluate the effectiveness of the market review in identifying opportunities for market entry,
growth, and differentiation.
Assess whether potential threats and challenges, such as competition, regulatory constraints, and
market saturation, have been adequately addressed.
5. Actionable Insights and Recommendations:
Determine the extent to which the market review provides actionable insights and
recommendations for marketing, sales, and product development strategies.
Evaluate the feasibility and impact of proposed strategies in addressing market gaps, leveraging
competitive advantages, and capitalizing on emerging opportunities.
6. Consideration of Limitations:

Group No 40 Panipat Institute of Engineering and Technology Page 36

 An Approach To Optimizing AI Application Tracking System

Acknowledge any limitations or biases inherent in the market review process, such as sample size
limitations, selection bias, or reliance on secondary data sources.
Consider how these limitations may affect the validity and generalizability of the findings and
recommendations.
7.Iterative Improvement:
Identify areas for improvement in future market reviews, such as expanding the scope of research,
incorporating primary data collection methods, or enhancing analytical rigor.
Emphasize the importance of continuous learning and adaptation based on feedback and evolving
market dynamics.
By critically evaluating the market review, you can ensure that the insights and recommendations
generated are robust, actionable, and aligned with the strategic objectives of the system

3.10 Conclusion
Chapter 3 includes review of the literature of the past to establish a baseline for the proposed
project. Under literature review, existing systems have been studied to gather knowledge in the
area of the study; what features are new in the market and what all features the developer can
integrate into his new system. The chapter also includes the information and resources that are a
part of the literature review and are studies or will be studied in future to collect the data and
information about the area of study.

Group No 40 Panipat Institute of Engineering and Technology Page 37

 An Approach To Optimizing AI Application Tracking System

CHAPTER 4: RESEARCH METHODS

4.1.1 Primary Research

Primary research involves gathering original data directly from the source, rather than relying on
existing data or secondary sources. In the context of the "Enhancing Candidate Experience: An
Approach To Optimizing AI Application Tracking System" system, primary research could
involve several methods to gather insights directly from target users, stakeholders, and industry
experts. Here's how primary research could be conducted:

4.1.2 Questionnaire
A Questionnaire consists of a number of questions printed in a piece of paper in a definite order to
elicit necessary information from the target users within a short duration. The Questionnaire is
provided to the respondents who are expected to read and understand the questions and write down
the reply in the space provided. Since, user is the types of users for the proposed system; the
developer will distribute the questionnaire among them.

1.Surveys and Questionnaires:

Design and distribute surveys or questionnaires to recruiters, HR professionals, and job applicants
to gather feedback on their resume screening processes, pain points, and preferences.Include
questions about the effectiveness of existing resume parsing tools, desired features in a resume
analyzer system, and willingness to adopt AI-driven solutions.
2.Interviews and Focus Groups:
Conduct one-on-one interviews or focus group discussions with key stakeholders, such as HR
managers, talent acquisition specialists, and technology decision-makers.
Explore in-depth insights into their workflow, challenges in resume screening, expectations from
resume analysis tools, and factors influencing purchasing decisions.
3.Prototype Testing:
Develop a prototype or demo version of the system and conduct usability testing sessions with
potential users.
Gather feedback on the user interface, feature set, accuracy of recommendations, and overall user
experience to identify areas for improvement.

Group No 40 Panipat Institute of Engineering and Technology Page 38

 An Approach To Optimizing AI Application Tracking System

4.Observational Research:
Observe recruiters or HR professionals as they conduct resume screening and analysis tasks in
their daily workflow.
Document their behavior, decision-making processes, pain points, and interactions with existing
tools or systems to uncover insights into their needs and preferences.
5.Market Trials and Pilots:
Collaborate with early adopters or pilot customers to deploy the system in real-world scenarios.
Monitor usage patterns, performance metrics, and user feedback during the trial period to evaluate
the system's effectiveness and gather insights for refinement.
6. Expert Consultations:
Seek input from domain experts, NLP researchers, and AI practitioners to validate the system's
approach, algorithms, and technological feasibility.
Leverage their expertise to identify best practices, emerging trends, and potential pitfalls in resume
analysis and NLP applications.
4.1.3 Interview
Interview is a type of primary research method in which a set of questions are pre-planned and are
asked to the interviewee face to face. The questions are generally open ended. It is designed to
assemble detailed information about a topic. For the proposed system, those questions are asked
in the interviews whose answers require bit detail description to understand the requirement. The
interviewees for the proposed system is developer. The purpose was to get an exclusive view of
the users to gather maximum information about the system requirements.

4.2 Secondary Research

Secondary research is usually conducted prior to primary research. It means gathering information
from already published books, journals, research papers which are third party authenticated
sources. It is done to learn from the mistakes that others have committed on the related domain
because it is better to learn from other’s mistakes and save time rather than repeating the same
mistake.

Group No 40 Panipat Institute of Engineering and Technology Page 39

 An Approach To Optimizing AI Application Tracking System

4.2.1 Technical Research

This is related to the technical part of the research means research related to selection of platform,
programming language, database, technology and methodology. Conducting technical research for
the proposed project is a critical factor that can affect the implementation of the project and thus
is conducted before the system design and implementation phase begins. A wide-spread research
is conducted that compares various platforms, programming languages, databases, technologies,
methodologies and evaluates them to come to conclusion which would be chosen for the proposed
project.

Technical Review:
Technical research involves investigating existing technologies, methodologies, and solutions
relevant to the development of the "Resume AI Analyzer" system. Here's how technical research
could be conducted:
1.NLP Algorithms and Techniques:
Explore different NLP algorithms and techniques for text processing, entity recognition, sentiment
analysis, and semantic understanding.
Research state-of-the-art models such as BERT, GPT, and Transformer architectures for natural
language understanding tasks.
2.Resume Parsing Methods:
Investigate various resume parsing methods, including rule-based parsing, statistical parsing, and
machine learning-based parsing.
Explore techniques for extracting structured information from unstructured resume text, such as
named entity recognition and information extraction.
3.Machine Learning and AI:
Study machine learning algorithms and techniques relevant to resume analysis, such as
classification, clustering, and regression.
Research deep learning models and frameworks for NLP tasks, including recurrent neural
networks (RNNs), convolutional neural networks (CNNs), and transformer models.
4.Software Development Tools and Frameworks:
Explore programming languages, libraries, and frameworks suitable for building the "Resume AI
Analyzer" system.

Group No 40 Panipat Institute of Engineering and Technology Page 40

 An Approach To Optimizing AI Application Tracking System

Research NLP libraries such as NLTK, spaCy, and Hugging Face Transformers, as well as web
development frameworks for building user interfaces.
5.Resume Datasets and Corpora:
Identify publicly available datasets and corpora of resumes for training and testing the system.
Evaluate the quality, size, and diversity of available datasets to ensure representative training data
for the system.
6.APIs and Services:
Research APIs and web services for resume parsing, text analysis, and NLP tasks that can be
integrated into the system.
Evaluate the reliability, scalability, and cost-effectiveness of external services for enhancing the
functionality of the ATS system.

4.3 Conclusion
Chapter 4 is all about the research methods. The researcher conducted primary and secondary
research under which technical research was conducted to come to a final conclusion of user
requirements and technologies and tools to be used. Couple of research methods have been used
by the developer, which includes Questionnaires and Interviews. The research was necessary to
avoid waste of time in a later point of development phase. Now, the researcher is pretty sure of the
features to be included in the system and how to remove existing problems. The developer is
confident enough to implement the proposed app after performing extreme research related to
domain, technology, language, tools etc.

Group No 40 Panipat Institute of Engineering and Technology Page 41

 An Approach To Optimizing AI Application Tracking System

CHAPTER 5: ANALYSIS
5.1 Analysis of Questionnaire
Refer to appendix

5.1 Feedback of Questionnaire

Refer to appendix

5.1.1 Overall Conclusion of Questionnaire

The questionnaire analysis reveals valuable insights into the user experience and satisfaction levels
with the "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" system. Overall, users find the system easy to use, with a high level of accuracy in parsed
resume data. While many users appreciate the efficiency and gains of the valuable features like
resume parsing and keyword extraction, there are suggestions for improvement, especially in
enhancing the data privacy and security measures. Despite some concerns, the majority of users
express their satisfaction with the system and indicate a willingness to recommend it to others.
These findings highlight the areas for further refinement and development to ensure continued
success and user satisfaction with the system.
5.2.1 Overall Conclusion of Interview
Overall, the interview process provided valuable insights into the user experience and satisfaction
levels with the system. Users generally find the system easy to use, accurate, and efficient, with
valuable features such as resume parsing and keyword extraction enhancing the recruitment
process. While there are some areas for improvement, particularly in data privacy and security
measures. However, the majority of users express their satisfaction and contentment with the
system. They indicate a willingness to recommend it to others. These findings underscore the
system's effectiveness in streamlining resume screening processes and improving decision-making
for both applicants and recruiters, highlighting its potential for continued success and
development.

Similar to the conclusion of the questionnaire, the overall interpretation of an interview

summarises the key insights and findings derived from strong matched interviews. Unlike

Group No 40 Panipat Institute of Engineering and Technology Page 42

 An Approach To Optimizing AI Application Tracking System

questionnaire data, interview data are often qualitative in nature, providing in-depth insights into
participants' outlook, experiences, and opinions.

Additionally, the conclusion may reflect on the interview process itself, discussing any challenges
encountered, insights gained from interactions with participants, or reflections on the researcher's
role in the process. It aims to provide an all inclusive understanding of the qualitative findings and
their implications, ensuring that the insights gained from the interviews are successfully
communicated and understood.

Group No 40 Panipat Institute of Engineering and Technology Page 43

 An Approach To Optimizing AI Application Tracking System

CHAPTER 6: SYSTEM DESIGN

6.1 Introduction
The introduction section provides an overview of the resume analyzer system, outlining its
purpose, functionality, and the problem it aims to solve. It sets the context for the subsequent
discussion on the system's design and features. Key points to include in the introduction are:
1. Purpose: Explain why the resume analyzer system is being developed and its intended
goals. This could include improving efficiency in recruitment processes, enhancing
candidate screening, or automating resume analysis tasks.
2. Scope: Define the scope of the system, including the types of resumes it can analyze, the
features it offers, and the target users (e.g., recruiters, HR professionals, job seekers).
3. Overview: Provide a brief overview of the system's architecture and components,
highlighting what will be covered in the subsequent sections of the document.
6.2 UML Diagram
Outline of the designing of UML diagrams for the system:
1. Identify actors: Applicants, Recruiters, System Admin.
2. Use cases: Upload Resume, View Recommendations, Download Data, Generate Reports,
Admin Analysis.
3. Relationships: Connect actors to relevant use cases.
4. Identify classes: Resume, User, Recommendation, Report, Admin.
5. Attributes: Resume data (e.g., name, contact info, skills), User details (e.g., username,
password), Recommendation details (e.g., suggested skills), Report data (e.g., analysis
results).
6. Relationships: Define associations between classes (e.g., User uploads Resume, Admin
generates Report).
6.2.1 Sequential Diagram Design
Outline of the designing of Sequential diagrams for the system:
1. Scenario: User uploads a resume and receives recommendations.
2. Actors: Applicant, System.
3. Steps: Applicant uploads resume through the UI.
➔ System receives and processes the uploaded resume.

Group No 40 Panipat Institute of Engineering and Technology Page 44

 An Approach To Optimizing AI Application Tracking System

➔ System parses resume data using NLP techniques.

➔ System generates recommendations based on parsed data.
➔ System displays recommendations to the user through the UI.
1. Workflow: Resume parsing process.
➔ Steps:
➔ Start: User uploads resume.
➔ System receives and validates the uploaded file.
➔ System extracts text content from the resume document.
➔ System analyses text content using NLP techniques.
➔ System identifies key information such as skills and experience.
2. Components: Frontend UI, Backend Processing, Database Management, External
Services (e.g., NLP APIs).
3. Relationships: Illustrate dependencies between components (e.g., Frontend UI
communicates with Backend Processing for resume upload).
4. End: System completes parsing process and provides results.
These diagrams provide a visual representation of the system's structure, behaviour, and
interactions, aiding in the understanding, design, and implementation of the "Resume AI Analyzer"
system

6.2.2 Sequence Diagram for Resume Analyzer

Sequence diagrams in software engineering provide a visual representation of the interactions
between different objects or components within a system over time. They illustrate the flow of
messages or method calls between these objects, showing the sequence of events that occur to
accomplish a specific task or scenario. Sequence diagrams are particularly useful for depicting the
dynamic behaviour of systems, including the order of execution of operations, the exchange of
data between components, and the timing of these interactions. They help stakeholders,
developers, and designers understand the system's behaviour, identify potential issues or
bottlenecks, and ensure that the system functions as intended.

Group No 40 Panipat Institute of Engineering and Technology Page 45

 An Approach To Optimizing AI Application Tracking System

FIG 1. RESUME ANALYZER SEQUENCE DIAGRAM

6.2.3 Activity Diagram for Resume Analyzer

Group No 40 Panipat Institute of Engineering and Technology Page 46

 An Approach To Optimizing AI Application Tracking System

An activity diagram is a type of UML (Unified Modeling Language) diagram that visualizes the
flow of activities or actions within a system or process. It is used to model the workflow or
behavior of a system, showing how different activities are performed sequentially or concurrently.
Key Components of an Activity Diagram:
1. Activities:Activities represent the tasks or actions performed within the system. They are
depicted as rounded rectangles and can include actions such as "Upload Resume,"
"Analyze Data," or "Generate Report."
2. Transitions: Transitions show the flow of control between activities. They are represented
by arrows and indicate the sequence of activities in the workflow. Transitions may also
include conditions or triggers that determine when one activity leads to another.
3. Decision Points (Branches): Decision points, often depicted as diamonds, represent points
in the workflow where the sequence of activities may diverge based on certain conditions
or criteria. They are used to model decision-making processes within the system.
4. Forks and Joins: Forks represent points in the workflow where multiple activities can be
performed concurrently or in parallel. Joins indicate the merging of multiple parallel paths
back into a single flow.
5. Start and End Nodes: Start nodes indicate the beginning of the workflow, while end nodes
represent the completion or termination of the process. They are typically depicted as solid
circles or ovals.

FIG 2. SIMPLE ACTIVITY DIAGRAM

Group No 40 Panipat Institute of Engineering and Technology Page 47

 An Approach To Optimizing AI Application Tracking System

FIG 3. ACTIVITY DIAGRAM REPRESENTING HOW DATA EXTRACTION

HAPPENS FOR THE RESUME UNIT

6.3 Entity Relation Model

An Entity-Relationship (ER) model is a conceptual representation used in database design to
describe the relationships between entities (objects or concepts) within a system. It's particularly
useful for visualizing the structure of a database and defining how different entities relate to each
other.
Key Components of an Entity-Relationship Model:
1. Entities: Entities represent real-world objects or concepts within the system being
modelled. They are typically nouns, such as "Customer," "Product," or "Order."
2. Attributes:Attributes describe the properties or characteristics of entities. They are
depicted as ovals connected to entities and represent the data elements stored for each

Group No 40 Panipat Institute of Engineering and Technology Page 48

 An Approach To Optimizing AI Application Tracking System

entity. For example, attributes of a "Customer" entity might include "CustomerID,"

"Name," "Email," etc.
3. Relationships: Relationships represent the associations or connections between entities.
They describe how entities are related to each other and are typically depicted as lines
connecting entities. Relationships can be one-to-one, one-to-many, or many-to-many,
depending on the cardinality of the association.
4. Cardinality: Cardinality defines the number of instances of one entity that can be
associated with another entity through a relationship. It specifies the minimum and
maximum number of occurrences allowed in the relationship. Cardinality is indicated using
symbols such as "1" (one), "N" (many), or "0" (zero).

FIG 4. SAMPLE E-R DIAGRAM FOR RESUME ANALYZER

Group No 40 Panipat Institute of Engineering and Technology Page 49

 An Approach To Optimizing AI Application Tracking System

6.3.1 List of Entities

A list of common entities that might be found in the system:

1. Customer: Represents individuals or organizations who interact with a business or service.

2. Product: Represents goods or services offered by a business.
3. Order: Represents a request placed by a customer to purchase one or more products.
4. Employee: Represents individuals who work for an organization.
5. Supplier: Represents entities that provide goods or services to a business.
6. Inventory: Represents the stock of products or materials held by a business.
7. Invoice: Represents a document issued by a seller to a buyer, indicating the details of a
transaction.
8. Payment: Represents the transfer of money from a customer to a business to settle an
obligation.
9. Transaction: Represents a business activity or event, such as a purchase, sale, or payment.
10. Account: Represents a record of financial transactions and balances associated with a
customer or entity.
11. Reservation: Represents a request made by a customer to reserve a resource or service for
a future date or time.
12. Appointment: Represents a scheduled meeting or event, typically involving customers and
service providers.

6.4 Normalization

Normalization is the process of organizing data in a database efficiently to minimize redundancy

and dependency. It involves breaking down large tables into smaller, related tables and defining
relationships between them. The goal of normalization is to eliminate data anomalies such as
insertion, update, and deletion anomalies, ensuring data integrity and consistency.

The normalization process typically involves several normalization forms, including:

6.4.1 First Normal Form (1NF):

Group No 40 Panipat Institute of Engineering and Technology Page 50

 An Approach To Optimizing AI Application Tracking System

Ensures that each column in a table contains atomic values, meaning that there are no repeating
groups or multivalued attributes. To achieve 1NF, you split the table into smaller tables and ensure
that each attribute contains only single values.

6.4.2 Second Normal Form (2NF):

Ensures that non-key attributes are fully dependent on the primary key and not on a subset of the
primary key. This involves removing partial dependencies by splitting tables further and creating
relationships between them.

6.4.3 Third Normal Form (3NF):

Ensures that there are no transitive dependencies, meaning that non-key attributes are not
dependent on other non-key attributes. To achieve 3NF, you further decompose tables and remove
any attributes that depend on other non-key attributes.

Group No 40 Panipat Institute of Engineering and Technology Page 51

 An Approach To Optimizing AI Application Tracking System

6.6 Sample Resume Uploaded

FIG 5. SAMPLE RESUME

Group No 40 Panipat Institute of Engineering and Technology Page 52

 An Approach To Optimizing AI Application Tracking System

CHAPTER 7: IMPLEMENTATION
7.1 Introduction
After the completion of the design phase, the developer analyzed that it was necessary that the
requirements quoted down must meet the proposed system development schema. Implementation
phase is one of the most essential stages of any project as the developer would work to implement
the system design into a real system. Implementation phase involves the vivid usage of tools to
convert the design modules into a real working system. For working on the real system, the
prerequisite for the developer would be a programming language and a programming tool. The
developer chooses to work Android SDK and the development language chosen would be JAVA.
The developer had to undergo through a series of errors which was obstructing the implementation
tenure. This chapter further throws light on how the design has been implemented and what were
the shortcomings during the making of the system. Furthermore, list of problems are mentioned
and what were the probable solutions that were provided.

7.2 Tools used for Implementation

The developer has mentioned all the tools that has been used in the development of the system.

Group No 40 Panipat Institute of Engineering and Technology Page 53

 An Approach To Optimizing AI Application Tracking System

Category Tools
Programming Languages Python, JavaScript
NLP Libraries NLTK, spaCy, Gensim
Machine Learning Libraries scikit-learn, TensorFlow, PyTorch
Web Frameworks Flask, Django
Data Processing Pandas, NumPy
Web Scraping Beautiful Soup, Scrapy
Text Analysis Word2Vec, GloVe, FastText, LDA, NMF
Named Entity Recognition spaCy, NLTK
Sentiment Analysis Various libraries or APIs
Containerization Docker
Version Control Git
CI/CD Jenkins, Travis CI, CircleCI
Cloud Services AWS, Google Cloud, Microsoft Azure
Development Environment PyCharm, Visual Studio Code, Jupyter Notebook
Testing pytest, unittest
Linting Tools flake8, pylint
Visualization Matplotlib, Seaborn, Plotly
Documentation Jupyter Notebooks, Markdown
Report Generation PDFKit, ReportLab

Table 1 :Tools used for Implementation

7.3 Implementation Plan

7.3.1 Implementation Approach
This plan would give the developer an overview of the procedures involved to develop the real
system. A strategic plan is required to successfully complete a system. ‘Divide and conquer
approach’ is used to divide the system into separate modules to detect and recover from errors
easily. The plan is made to prioritize various modules on the basis of their complexity so that each
and every module can be implemented on time and the complex modules should be developed
first.

Group No 40 Panipat Institute of Engineering and Technology Page 54

 An Approach To Optimizing AI Application Tracking System

7.3.1 Implementation Approach Steps

1. Define objectives and target users.

2. Gather diverse resumes for analysis.

3. Clean and normalize text data.

4. Extract relevant features from resumes.

5. Convert text data into numerical features.

6. Choose appropriate machine learning models.

7. Train models using labeled data.

8. Optimize model hyperparameters.

9. Evaluate model performance using metrics.

10. Validate results with holdout set or cross-validation.

11. Integrate model with web framework.

12. Develop user-friendly interface.

13. Deploy application on cloud platform.

14. Ensure scalability and reliability.

15. Conduct unit tests for functionality verification.

16. Perform integration tests for module interaction.

17. Document implementation details and algorithms used.

18. Provide user documentation for interface.

19. Plan for regular updates and maintenance.

20. Monitor system performance and user feedback.

21. Gather input from stakeholders.

22. Collect labeled data for supervised learning.

Group No 40 Panipat Institute of Engineering and Technology Page 55

 An Approach To Optimizing AI Application Tracking System

23. Convert resumes to a uniform format.

24. Extract skills, experience, and education details.

25. Apply Named Entity Recognition (NER) for entity extraction.

26. Perform sentiment analysis for tone detection.

27. Optimize TF-IDF parameters for feature extraction.

28. Implement classification models for resume categorization.

29. Fine-tune model hyperparameters for optimization.

30. Use holdout set for model evaluation.

31. Conduct cross-validation for robustness assessment.

32. Develop web interface for user interaction.

33. Ensure compatibility with different browsers.

34. Utilize Docker for containerization.

35. Deploy applications on AWS or Google Cloud.

36. Configure auto-scaling for demand spikes.

37. Implement logging for error tracking.

38. Monitor resource utilization for optimization.

39. Design unit tests for individual components.

40. Develop integration tests for system modules.

41. Automate testing process with CI/CD pipeline.

42. Maintain version control with Git.

43. Ensure adherence to coding standards.

44. Document codebase for future reference.

45. Provide inline comments for code clarity.

Group No 40 Panipat Institute of Engineering and Technology Page 56

 An Approach To Optimizing AI Application Tracking System

46. Update documentation with new features.

47. Solicit user feedback for improvements.

48. Analyze user behavior for feature prioritization.

49. Collaborate with UX/UI designers for interface enhancements.

50. Conduct A/B testing for feature comparison.

51. Monitor application performance metrics.

52. Implement failover mechanisms for high availability.

53. Perform security audits for data protection.

54. Encrypt sensitive user data.

55. Restrict access to authorized personnel only.

56. Comply with GDPR regulations for data handling.

57. Perform regular backups for data recovery.

58. Establish disaster recovery protocols.

59. Train users on application usage.

60. Provide troubleshooting guides for common issues.

61. Offer customer support channels for assistance.

62. Collaborate with HR professionals for domain expertise.

63. Customize analysis based on industry requirements.

64. Develop features for multilingual support.

65. Ensure localization for global accessibility.

66. Conduct market research for competitive analysis.

67. Explore partnerships for feature expansion.

68. Engage in continuous learning for skill enhancement.

Group No 40 Panipat Institute of Engineering and Technology Page 57

 An Approach To Optimizing AI Application Tracking System

69. Attend conferences for industry insights.

70. Publish articles for knowledge sharing.

71. Monitor competitor offerings for benchmarking.

72. Engage in networking events for collaboration opportunities.

73. Establish strategic partnerships for growth.

74. Seek funding for expansion plans.

75. Leverage social media for brand awareness.

76. Participate in industry forums for thought leadership.

77. Collaborate with academic institutions for research.

78. Develop internship programs for talent acquisition.

79. Support open-source initiatives for community contribution.

80. Contribute to relevant standards bodies for industry advancement.

81. Advocate for diversity and inclusion in technology.

82. Mentor aspiring professionals in the field.

83. Organize hackathons for innovation.

84. Host workshops for skill development.

85. Participate in career fairs for recruitment.

86. Offer scholarships for underrepresented groups.

87. Support STEM education initiatives.

88. Provide resources for career advancement.

89. Promote work-life balance among employees.

90. Encourage continuous feedback and improvement.

91. Foster a culture of innovation and experimentation.

Group No 40 Panipat Institute of Engineering and Technology Page 58

 An Approach To Optimizing AI Application Tracking System

92. Recognize and reward employee contributions.

93. Encourage knowledge sharing across teams.

94. Support employee well-being programs.

95. Provide opportunities for professional development.

96. Foster a collaborative and inclusive work environment.

97. Promote transparency in decision-making processes.

98. Emphasize ethical business practices.

99. Commit to corporate social responsibility.

100. Strive for excellence in all endeavors.

7.4 Traceability of Implementation Modules with Design

Functionality (Modules) Sequence Diagram

Resume Builder System SD – 01

Resume Analyzer SD – 02

Input Extraction SD – 03

Smart Resume System SD – 01

Table 2 :Traceability of Implementation Modules with Design

7.5 Implementation of Complex Modules

Named Entity Recognition (NER): Use NLP libraries like spaCy or NLTK to identify entities
such as names, organizations, skills, etc., from resumes.

Fine-tune pre-trained NER models on domain-specific data for better accuracy.Implement post-
processing techniques to improve entity recognition, such as rule-based filtering and context-based
disambiguation.

Group No 40 Panipat Institute of Engineering and Technology Page 59

 An Approach To Optimizing AI Application Tracking System

Sentiment Analysis: Utilize pre-trained sentiment analysis models or train your own on labeled
data to classify the sentiment of resume content (positive, negative, neutral).

Consider the context and language nuances to enhance the accuracy of sentiment classification.

Implement techniques like feature engineering and ensemble methods to improve model
performance.

Topic Modeling: Use algorithms like Latent Dirichlet Allocation (LDA) or Non-negative Matrix
Factorization (NMF) to discover latent topics from resumes.

Preprocess text data by tokenization, stemming, and removing stopwords to improve the quality
of topic modeling.

Evaluate topic coherence and model perplexity to assess the quality of generated topics.

Resume Parsing: Develop parsers to extract structured information from resumes, such as contact
details, work experience, education, etc.

Utilize regular expressions or custom parsing algorithms to identify and extract relevant
information accurately.

Handle variations in resume formats and structures by incorporating robust error handling
mechanisms.

Skills Matching: Build a skills matching module to match the skills mentioned in resumes with
the required skills in job descriptions.

Use techniques like keyword matching, semantic similarity, or machine learning classifiers to
identify relevant skills.

Implement algorithms to quantify the proficiency level of skills mentioned in resumes based on
context and experience.

Experience Extraction: Develop algorithms to extract detailed information about work

experience, including job titles, company names, tenure, responsibilities, etc.

Group No 40 Panipat Institute of Engineering and Technology Page 60

 An Approach To Optimizing AI Application Tracking System

Use NLP techniques to identify temporal expressions and extract chronological order of work
experiences.

Handle complex structures in resumes, such as bullet points, paragraphs, and nested sections, to
accurately extract experience details.

Education Parsing: Design parsers to extract educational qualifications from resumes, including
degree names, institutions, graduation dates, GPA, etc.

Utilize heuristics and pattern matching to identify educational credentials in different formats and
languages.

Implement validation checks to ensure the consistency and accuracy of extracted education
information.

Keyword Extraction: Develop algorithms to extract keywords and phrases that are relevant to
specific job roles or industries from resumes.

Use TF-IDF, Text Rank, or other keyword extraction techniques to identify important terms based
on their frequency and importance in the context.

Implement filtering mechanisms to remove noise and irrelevant keywords from the extracted list.

Document Similarity: Implement document similarity algorithms to measure the similarity

between resumes and job descriptions.

Use techniques like cosine similarity, Jaccard similarity, or word embeddings to quantify the
similarity score.

Incorporate thresholding mechanisms to classify resumes based on their relevance to specific job
postings.

Error Handling and Logging: Develop robust error handling mechanisms to handle exceptions
and edge cases gracefully.

Implement logging functionality to record system events, errors, and user interactions for
troubleshooting and analysis purposes.

Group No 40 Panipat Institute of Engineering and Technology Page 61

 An Approach To Optimizing AI Application Tracking System

Use logging frameworks like log4j or Python's logging module to manage log levels and log
output.

Scalability and Performance Optimization: Design modules with scalability in mind to handle
large volumes of resumes efficiently.

Optimize algorithms and data structures to minimize computational overhead and memory usage.

Utilize caching mechanisms and distributed processing techniques to improve system

performance.

User Interface Design: Design intuitive and user-friendly interfaces for uploading resumes,
viewing analysis results, and interacting with the system.

Incorporate responsive design principles to ensure compatibility with different devices and screen
sizes.

Conduct usability testing and iterate on design based on user feedback to enhance user experience.

7.6 Technical Quality and Other Features

7.6.1 Memory Utilization
Streaming Processing: Implement streaming processing techniques to read and process resumes
sequentially from disk or database instead of loading them all into memory simultaneously.

Lazy Loading: Adopt lazy loading mechanisms to load data on-demand only when needed, rather
than loading everything into memory upfront. This can significantly reduce memory footprint,
especially for large datasets.

Memory Profiling: Use memory profiling tools to identify memory-intensive operations and
optimize them. Tools like memory_profiler for Python can help in identifying memory hotspots
and memory leaks.

Garbage Collection Optimization: Optimize garbage collection settings to reclaim memory

efficiently. Tune garbage collection parameters based on application requirements and workload
characteristics.

Group No 40 Panipat Institute of Engineering and Technology Page 62

 An Approach To Optimizing AI Application Tracking System

Memory Caching: Implement memory caching mechanisms to cache frequently accessed data in
memory, reducing the need for repeated disk or database access. Use caching libraries like Redis
or Memory cached for efficient memory caching.

Resource Management: Monitor memory usage and resource consumption regularly. Set
resource limits and thresholds to prevent memory exhaustion and ensure stable performance.

Parallelism and Concurrency: Utilize parallelism and concurrency to distribute memory-

intensive tasks across multiple processes or threads. This can help in utilizing available memory
more effectively and improving overall throughput.

Resource Release: Release memory resources promptly after they are no longer needed. Close
file handles, database connections, and other resources to free up memory and avoid memory leaks.

Memory-efficient Algorithms: Use memory-efficient algorithms and data structures wherever

possible. For example, prefer iterative algorithms over recursive ones to avoid excessive stack
usage.

7.6.2 Performance
Firstly, accuracy is paramount. The analyzer must reliably extract and interpret information from
resumes, such as skills, experience, and education. High accuracy ensures trustworthy insights for
decision-making. Speed is also vital; quick processing enables timely decisions by recruiters and
hiring managers. Scalability is another aspect, determining the analyzer's ability to handle
increasing workloads and large volumes of resumes efficiently. User satisfaction is crucial,
influenced by the analyzer's user-friendly interface, intuitive design, and accurate results. A robust
analyzer can handle diverse resume formats, languages, and data quality without crashing or
producing errors. Adaptability allows the analyzer to adjust to changing requirements and
preferences seamlessly. Integration capabilities ensure smooth interaction with other systems and
workflows, enhancing efficiency. Maintenance is essential for continued reliability, involving
regular updates, bug fixes, and enhancements. Ultimately, a high-performing resume analyzer
balances accuracy, speed, scalability, user satisfaction, robustness, adaptability, integration, and
maintenance, ensuring its effectiveness over time.

Group No 40 Panipat Institute of Engineering and Technology Page 63

 An Approach To Optimizing AI Application Tracking System

7.6.3 User Interface

⮲ The interface typically includes features for uploading resumes, initiating analysis, and
viewing analysis results. Users should be able to easily upload resumes in various formats,
such as PDF, DOCX, or plain text, through a simple and accessible upload mechanism.
Once the resumes are uploaded, users can initiate the analysis process with a single click
or by selecting specific analysis options, such as skill matching, sentiment analysis, or topic
modeling.

⮲ During the analysis process, users may be presented with progress indicators or status
updates to keep them informed about the processing status. Once the analysis is complete,
the interface should display the analysis results in a structured and organized format. This
may include a summary of key findings, visualizations of analysis outcomes (such as word
clouds, topic clusters, or sentiment scores), and detailed breakdowns of extracted
information (such as skills, experience, and education).

⮲ Additionally, the interface should offer options for further exploration and interaction with
the analysis results. Users may be able to filter and sort the results based on specific criteria,
drill down into detailed information, or export the results for further analysis or sharing.
Interactive elements such as clickable links, tooltips, and hover-over effects can enhance
usability and provide additional context or explanations where needed

7.6.4 Naming Conventions

Component Naming Convention

Main Module resume_analyzer.py

Data Collection data_collector.py
Preprocessing preprocessing.py
Feature Extraction feature_extraction.py
Model Building model_builder.py
Text Analysis text_analysis.py
Named Entity Recognition named_entity_recognition.py

Group No 40 Panipat Institute of Engineering and Technology Page 64

 An Approach To Optimizing AI Application Tracking System

Component Naming Convention

Sentiment Analysis sentiment_analysis.py

Topic Modeling topic_modeling.py
Resume Parsing resume_parser.py
Skills Matching skills_matching.py
Experience Extraction experience_extraction.py
Education Parsing education_parser.py
Keyword Extraction keyword_extraction.py
Document Similarity document_similarity.py
Error Handling error_handling.py
Logging logger.py
Caching caching.py
Parallel Processing parallel_processing.py
Resource Management resource_management.py
Garbage Collection garbage_collection.py
Memory Profiling memory_profiling.py
Unit Testing test_module_name.py (e.g., test_feature_extraction.py)
Integration Testing integration_test_module_name.py
User Interface user_interface.py
Deployment deployment.py
Documentation documentation.py
Maintenance maintenance.py
Configuration config.py
Utilities utils.py
Table 3 :Naming Conventions

Group No 40 Panipat Institute of Engineering and Technology Page 65

 An Approach To Optimizing AI Application Tracking System

7.6.5 Comments
Comments are one of the most significant aspects which describe the application technical quality.
It supports the developer in re-reading the source code after a long time. Thus, relevant comments
are provided for understanding.

Module and Function Comments:

# Module: data_collector.py

# Description: This module contains functions for collecting resumes from various sources.

def fetch_resumes(url):

""

Fetch resumes from the specified URL.

Args:

url (str): The URL from which to fetch resumes.

Returns:

list: A list of resumes fetched from the URL.

""

Class Comments:

class ResumeAnalyzer:

""

Class for analyzing resumes and extracting relevant information.

"""

def __init__(self):

"""

Initialize the ResumeAnalyzer object.

Group No 40 Panipat Institute of Engineering and Technology Page 66

 An Approach To Optimizing AI Application Tracking System

"""

Function Comments:

def extract_skills(resume_text):

"""

Extract skills from the given resume text.

Args:

resume_text (str): The text content of the resume.

Returns:

list: A list of skills extracted from the resume.

""

Inline Comments:

# Iterate through each resume and extract skills

for resume in resumes:

skills = extract_skills(resume)

Commenting Complex Logic:

# Calculate TF-IDF scores for each term in the vocabulary

tfidf_vectorizer = TfidfVectorizer(...)

tfidf_matrix = tfidf_vectorizer.fit_transform(corpus)

TODO Comments:

# TODO: Implement caching mechanism to improve performance

Explanation of Constants and Magic Numbers:

Group No 40 Panipat Institute of Engineering and Technology Page 67

 An Approach To Optimizing AI Application Tracking System

# Define the maximum number of resumes to process

MAX_RESUMES = 100

Documentation Comments:

"""

Module: data_collector.py

Description: Contains functions for collecting resumes from various sources.

"""

7.7 User Manual

This manual provides very simple and quick steps for running this application by walking you
through the Sample Tasks.

Group No 40 Panipat Institute of Engineering and Technology Page 68

 An Approach To Optimizing AI Application Tracking System

Group No 40 Panipat Institute of Engineering and Technology Page 69

 An Approach To Optimizing AI Application Tracking System

7.8 Technical Manual

Developer Note: make sure your mobile device is rooted with USB debugging enabled on it. To
install & run this a user needs to do the following things on the phone.

Group No 40 Panipat Institute of Engineering and Technology Page 70

 An Approach To Optimizing AI Application Tracking System

Group No 40 Panipat Institute of Engineering and Technology Page 71

 An Approach To Optimizing AI Application Tracking System

CHAPTER 8: TESTING
“... we have as many testers as we have developers. And testers spend all their time testing, and
developers spend half their time testing. We're more of a testing, a quality software organization
than we're a software organization.” – Bill Gates
(Information Week 2002)

8.1 Introduction
In the context of a resume analyzer system, the introduction provides an overview of the purpose,
scope, and significance of the system. It briefly outlines the problem it aims to solve, its intended
users, and the key features it offers. Additionally, the introduction may touch upon the benefits of
using the system and its potential impact on the recruitment process. Overall, the introduction sets
the stage for the subsequent sections of the documentation, providing context and framing the
discussion of the system's design and functionality.
8.2 Need of Testing
The need for testing in software development, including for a resume analyzer system, is
paramount for several reasons:

• Quality Assurance: Testing ensures that the system functions as intended and meets the
specified requirements. It helps identify defects, errors, or inconsistencies in the software,
thereby improving its quality and reliability.
• Bug Detection: Testing helps uncover bugs, glitches, or issues in the system's
functionality, user interface, or performance. By detecting and fixing these bugs early in
the development process, potential problems can be addressed before they impact users.
• User Satisfaction: Thorough testing leads to a more stable and user-friendly system. By
ensuring that the system works smoothly and efficiently, testing enhances the user
experience and increases user satisfaction.
• Risk Mitigation : Testing helps mitigate risks associated with software development, such
as technical failures, security vulnerabilities, or compliance issues. By identifying and

Group No 40 Panipat Institute of Engineering and Technology Page 72

 An Approach To Optimizing AI Application Tracking System

addressing potential risks through testing, the likelihood of costly failures or disruptions is
reduced.
• Compliance Requirements: In certain industries or domains, compliance with regulatory
standards or industry guidelines is mandatory. Testing helps ensure that the software meets
these compliance requirements and adheres to relevant standards and regulations.
• Continuous Improvement: Testing is an iterative process that allows for continuous
improvement and refinement of the software. By collecting feedback, identifying areas for
improvement, and making necessary adjustments, testing contributes to the ongoing
enhancement of the system's functionality and performance.
• Cost Savings: Identifying and fixing defects early in the development process is typically
less costly than addressing them later, after the software has been deployed. Testing helps
minimize the cost of rework, maintenance, and support by preventing issues from
escalating into larger problems

8.3 Test Plan

A test plan is a document that outlines the objectives, scope, approach, resources, and schedule for
testing a software system. It defines the goals of the testing effort, specifies what will be tested,
and details how testing will be conducted. The plan also identifies the test environment, schedules
testing activities, assigns responsibilities, and outlines risk mitigation strategies. It serves as a
roadmap for the testing process, ensuring that testing is conducted systematically and effectively
to meet project requirements and quality standards.

8.3.1 Type of Testing

Software testing encompasses various types to ensure quality and reliability. Unit testing verifies
individual components' correctness, integration testing validates interactions between integrated
modules, and functional testing confirms that the system performs as intended. Regression testing
ensures that modifications do not adversely affect existing functionality, while acceptance testing
assesses if the software meets user requirements. Performance testing evaluates responsiveness
and scalability, and security testing identifies vulnerabilities. Usability testing gauges user-
friendliness, while compatibility testing ensures seamless operation across different platforms.

Group No 40 Panipat Institute of Engineering and Technology Page 73

 An Approach To Optimizing AI Application Tracking System

Localization and internationalization testing validate support for diverse languages and cultures.
Each type of testing plays a crucial role in ensuring software quality and meeting user expectations,
ultimately contributing to the success of the project.

FIG 1. TYPES OF TESTING

Integration Testing:
● Test the interactions and interfaces between different components or modules of the
software.
● Verify that integrated components work together as expected.
● Identify and address issues related to communication, data exchange, and dependency
management.

Functional Testing:
● Test the functional requirements of the software.

Group No 40 Panipat Institute of Engineering and Technology Page 74

 An Approach To Optimizing AI Application Tracking System

● Verify that the system performs its intended functions correctly.

● Test cases are derived from specifications, user stories, or use cases.

Regression Testing:
● Test the software after making changes or updates to ensure that existing functionality has
not been adversely affected.
● Re-run previously executed tests to verify that all existing features still work correctly.
● Helps prevent regression issues and ensures backward compatibility.

Acceptance Testing:
● Test the software from the perspective of end-users to determine if it meets their
requirements and expectations.
● Verify that the software fulfills the acceptance criteria specified by stakeholders.
● May include user acceptance testing (UAT) conducted by end-users or business
representatives.

Performance Testing:
● Test the performance characteristics of the software, such as responsiveness, scalability,
and stability, under various conditions.
● Identify performance bottlenecks, resource limitations, and areas for optimization.
● Includes load testing, stress testing, and endurance testing.

Security Testing:
● Test the security features and controls of the software to identify vulnerabilities, threats,
and risks.
● Verify that the software protects against unauthorized access, data breaches, and other
security threats.
● Includes penetration testing, vulnerability scanning, and security audits.

Usability Testing:

Group No 40 Panipat Institute of Engineering and Technology Page 75

 An Approach To Optimizing AI Application Tracking System

● Test the usability and user-friendliness of the software from the perspective of end-users.
● Evaluate the effectiveness, efficiency, and satisfaction of users when interacting with the
software.
● Identify usability issues, accessibility barriers, and areas for improvement.

Compatibility Testing:
● Test the compatibility of the software with different operating systems, browsers, devices,
and environments.
● Ensure that the software works correctly across various platforms and configurations.
● Includes cross-browser testing, cross-device testing, and interoperability testing.
8.3.2 Pass/Fail Criteria

Pass/fail criteria in software testing are defined through:

⮲ Expected Outcomes: Criteria are established based on expected behaviors and outcomes
defined in test cases or requirements documentation.

⮲ Tolerance Levels: Allowable deviations from expected outcomes are defined, considering
factors like margin of error or environmental constraints.

⮲ Acceptance Standards: Criteria are aligned with stakeholder or end-user expectations,

quality standards, and performance metrics to determine if the software meets requirements
and is ready for release.

Group No 40 Panipat Institute of Engineering and Technology Page 76

 An Approach To Optimizing AI Application Tracking System

8.4 Point of Contact of Troubleshooting Purpose

Table 1 : POINT OF CONTACT OF TROUBLESHOOTING PURPOSE

Group No 40 Panipat Institute of Engineering and Technology Page 77

 An Approach To Optimizing AI Application Tracking System

8.5 Criteria of Test Cases

Test case criteria are essential components used to evaluate the success or failure of individual test
cases. They provide clear guidelines and expectations for testing activities, ensuring thorough
validation of the system's functionality and performance. Here's a breakdown of each criterion:

⮲ Test Case ID: Unique identifier facilitating easy reference and tracking.
⮲ Test Case Description: Concise outline of test case objectives, actions, and expected
outcomes.
⮲ Test Steps: Sequential instructions detailing test execution procedures, including
prerequisites and actions.
⮲ Expected Results: Clear statements defining anticipated system behavior or outcomes.
⮲ Actual Results: Recorded observations and outcomes observed during test execution.
⮲ Pass/Fail Status: Determination of test case success (pass) or failure (fail) based on actual
versus expected results.
⮲ Comments/Notes: Additional context, observations, or explanations related to test
execution or outcomes, aiding further analysis or resolution.

8.7 Technical requirements for Testing

The technical requirements for testing encompass various aspects crucial for ensuring the
effectiveness and efficiency of the testing process. This includes setting up dedicated test
environments that closely mimic production setups, providing the necessary infrastructure and
hardware resources to support testing activities, and leveraging virtualization technologies for
efficient environment management. Additionally, organizations need to utilize testing tools for
automation, management, and monitoring, integrating testing seamlessly into the development and
deployment pipelines to enable continuous validation of code changes. Proper data management
procedures are essential to handle test data securely while ensuring integrity and privacy.
Scalability and performance testing help assess the system's capabilities under different load
conditions, while stringent security measures and compliance with regulatory standards ensure
data protection and regulatory adherence. By addressing these technical requirements,

Group No 40 Panipat Institute of Engineering and Technology Page 78

 An Approach To Optimizing AI Application Tracking System

organizations can establish robust testing practices, leading to improved software quality,
reliability, and performance.

Table 2 : Technical requirements for troubleshooting purposes

8.8 Users Involved in Testing

The developer will play the role of tester.
8.9 Unit Testing
In the context of a resume analyzer, unit testing involves testing individual components or modules
of the system in isolation to ensure their functionality. Each component, such as the text extraction
module or the natural language processing (NLP) module, is tested independently to verify that it
performs as expected and meets its design specifications. For example, unit tests might verify that
the text extraction module accurately extracts text from resume documents, while another set of
unit tests might validate the NLP module's ability to analyze and extract relevant information from
the extracted text. Unit testing in a resume analyzer helps identify and fix defects early in the
development process, ensuring that each component works correctly before integrating them into

Group No 40 Panipat Institute of Engineering and Technology Page 79

 An Approach To Optimizing AI Application Tracking System

the larger system. This approach contributes to the overall reliability, accuracy, and performance
of the resume analyzer software.

8.9.1 Justification for unit Testing

Unit testing is justified in the development of a resume analyzer for several reasons:

• Early Detection of Defects: Unit testing allows developers to identify and address defects
in individual components early in the development process. By testing each unit of code in
isolation, defects can be caught and fixed before they escalate into more significant issues,
reducing the overall cost and effort of debugging and maintenance.
• Improved Code Quality: Unit testing encourages developers to write modular, well-
structured code that is easier to test and maintain. Writing tests for each unit of code helps
ensure that it meets its intended functionality and adheres to design specifications, leading
to higher code quality and reliability.
• Regression Prevention: Unit tests serve as a safety net against regression bugs, ensuring
that changes to one part of the codebase do not inadvertently break functionality in other
areas. By running unit tests regularly, developers can quickly identify and address
regressions, maintaining the integrity of the resume analyzer software throughout the
development process.
• Facilitates Refactoring: Unit testing provides confidence to developers when refactoring
or making changes to the codebase. With a comprehensive suite of unit tests in place,
developers can refactor code with the assurance that existing functionality will not be
compromised, leading to more agile and efficient development cycles.
• Enables Continuous Integration: Unit testing is a foundational aspect of continuous
integration (CI) and continuous delivery (CD) practices. By automating unit tests and
integrating them into the CI/CD pipeline, developers can ensure that changes are

Group No 40 Panipat Institute of Engineering and Technology Page 80

 An Approach To Optimizing AI Application Tracking System

thoroughly tested and validated before being deployed to production, reducing the risk of
introducing bugs and errors.

8.9.2 Black box testing (Functional Testing)

FIG 2. Black box Testing and Approach

Black box testing is a software testing technique where the internal workings of the system under
test are not known to the tester. Instead, the tester focuses on the external behavior and
functionality of the software, treating it as a "black box" where inputs are provided, and outputs

Group No 40 Panipat Institute of Engineering and Technology Page 81

 An Approach To Optimizing AI Application Tracking System

are observed. In black box testing, the tester does not have access to the source code and does not
need knowledge of the internal implementation details.

Justification for Black Box Testing

Black box testing ensures software functionality aligns with user expectations without requiring
knowledge of internal code. It validates system behavior from an end-user perspective, identifying
defects and ensuring compliance with specified requirements. This approach facilitates unbiased
assessment, thorough test coverage, and validation of software usability and functionality. Overall,
black box testing enhances software quality, reliability, and user satisfaction.

Login_Module

FIG 3 Login module

Group No 40 Panipat Institute of Engineering and Technology Page 82

 An Approach To Optimizing AI Application Tracking System

8.9.3 White Box Testing (Conceptual Testing)

White box testing, also known as structural testing or glass box testing, is a software testing
technique that involves examining the internal structure, design, and implementation of the
software.

The primary goal of white box testing is to ensure that all paths and branches of the code are tested
thoroughly, with the aim of uncovering defects related to logic errors, boundary conditions, and
code optimization. Test cases are designed based on an understanding of the code structure and
execution paths, with the objective of achieving maximum code coverage, typically measured by
metrics such as statement coverage, branch coverage, and path coverage.

White box testing techniques include statement coverage, branch coverage, path coverage, and
condition coverage, among others. These techniques help identify areas of the code that have not
been executed during testing, enabling testers to design additional test cases to achieve
comprehensive coverage.

Update Profile

Table 4: Update profile

Group No 40 Panipat Institute of Engineering and Technology Page 83

 An Approach To Optimizing AI Application Tracking System

Code:

Group No 40 Panipat Institute of Engineering and Technology Page 84

 An Approach To Optimizing AI Application Tracking System

8.10 Integration Testing

Integration testing in a resume analyzer involves testing the interaction and communication
between different components, modules, and external systems to ensure that they work together
seamlessly and achieve the desired functionality. These test scenarios cover various aspects of
integration, including data flow, API communication, database interaction, user interface
functionality, and integration with third-party software or services.

Group No 40 Panipat Institute of Engineering and Technology Page 85

 An Approach To Optimizing AI Application Tracking System

Table 5: Integration Testing

Table 6: Comparison between unit testing and integration Testing

8.10. Technique used for Integration Testing

Group No 40 Panipat Institute of Engineering and Technology Page 86

 An Approach To Optimizing AI Application Tracking System

Integration testing in a resume analyzer employs several techniques to ensure that different
components, modules, and external systems integrate seamlessly and function correctly as a
unified system. One common technique is the top-down approach, where testing begins with
high-level modules and progresses downward, gradually integrating lower-level modules.
Conversely, the bottom-up approach starts with testing individual modules and progressively
integrates them upward.
Another technique is the big bang approach, where all modules are integrated simultaneously for
testing. Additionally, incremental integration involves gradually adding and testing new modules
until the entire system is integrated.
These techniques help identify integration issues, such as communication failures, data
inconsistencies, and interface mismatches, ensuring that the resume analyzer functions as
intended and meets user requirements.

8.10.2 Justification for Integration Testing

Table 6: justification

Group No 40 Panipat Institute of Engineering and Technology Page 87

 An Approach To Optimizing AI Application Tracking System

8.11 System Testing

System testing is a comprehensive software testing technique that evaluates the entire system as a
whole. Unlike unit testing and integration testing, which focus on individual components or the
integration of components, system testing assesses the system's behavior and functionality in its
entirety. This testing phase ensures that the software meets specified requirements and functions
correctly in its intended environment.

In system testing, the software is tested against the functional and non-functional requirements to
validate its behavior and performance. Test scenarios cover various aspects such as user
interactions, data flow, error handling, security, compatibility, and reliability. System testing may
involve both manual and automated testing techniques to execute test cases and validate system
behavior.

Fig
4. System Testing

Group No 40 Panipat Institute of Engineering and Technology Page 88

 An Approach To Optimizing AI Application Tracking System

8.11.1 Justification for System Testing

• Validation of Requirements: System testing ensures that the software meets specified
requirements and functions as intended in its operational environment.
• Assurance of Quality: It validates the overall quality, functionality, and performance of the
software, identifying defects and ensuring they are addressed before deployment.
• Mitigation of Risks: System testing helps mitigate risks associated with software failures,
ensuring reliability, security, and compliance with regulatory standards.
• User Satisfaction: By validating the software from an end-to-end perspective, system
testing ensures that it meets user expectations and delivers a satisfactory user experience.
• Confidence in Deployment: Successful system testing instills confidence in stakeholders,
including developers, testers, and end-users, that the software is ready for deployment and
uses

8.11.2 System Testing for User Module

System testing for a user mobile involves comprehensive evaluation of the entire mobile
application as a unified system to ensure it meets specified requirements and functions seamlessly
in its intended environment. This testing phase focuses on validating the functionality, usability,
compatibility, security, and performance of the mobile application across diverse devices,
platforms, and operating system versions. System testing ensures that all features and
functionalities work as expected, providing a seamless and intuitive user experience. It also verifies
the integration of backend services, APIs, and third-party components, ensuring smooth
communication and data exchange within the mobile ecosystem. Additionally, system testing
assesses the mobile application's adherence to security standards and regulatory requirements,
safeguarding user data and ensuring compliance with privacy laws. By identifying and addressing
issues related to stability, reliability, and performance, system testing ensures the delivery of a

Group No 40 Panipat Institute of Engineering and Technology Page 89

 An Approach To Optimizing AI Application Tracking System

robust and dependable mobile application that meets user expectations and drives business success
in the competitive mobile market.
8.12 Compatibility Testing

Compatibility testing is a software testing technique used to assess the compatibility of an

application or system across different environments, platforms, devices, and configurations. It
ensures that the software functions correctly and delivers a consistent user experience across
various combinations of operating systems, web browsers, devices, and network conditions.The
primary goal of compatibility testing is to identify any compatibility issues or inconsistencies that
may arise when the software is deployed in different environments. This includes testing the
application's compatibility with different versions of operating systems (e.g., Windows, macOS,
Linux), web browsers (e.g., Chrome, Firefox, Safari, Edge), mobile devices (e.g., iOS, Android),
screen sizes, resolutions, and network configurations.

Fig 6. Compatibility Testing

Compatibility testing involves executing test cases on multiple combinations of platforms and
configurations to verify that the software performs as expected and remains functional across all
supported environments. It helps ensure that users can access and use the software seamlessly
regardless of the device or platform they are using.
By conducting compatibility testing, organizations can identify and address compatibility issues
early in the development lifecycle, minimizing the risk of user dissatisfaction, loss of business,
and negative impact on brand reputation. Overall, compatibility testing plays a crucial role in

Group No 40 Panipat Institute of Engineering and Technology Page 90

 An Approach To Optimizing AI Application Tracking System

delivering a high-quality, reliable, and user-friendly software product that meets the diverse needs
of users across different environments and platforms.

8.13 GUI Testing

GUI testing, or Graphical User Interface testing, is a software testing technique that focuses on
evaluating the graphical elements and user interface components of an application to ensure they
function correctly and provide a positive user experience. GUI testing verifies that the user
interface elements, such as buttons, menus, forms, dialog boxes, and navigation controls, are
displayed correctly, respond appropriately to user interactions, and adhere to design specifications
and usability guidelines.

The primary goal of GUI testing is to validate the visual appearance, layout, functionality, and
usability of the application's graphical interface. This includes testing aspects such as screen
resolution, font sizes, color schemes, alignment of elements, consistency of user interface elements
across different screens, and responsiveness to user inputs (e.g., mouse clicks, keyboard inputs,
touch gestures).

Fig 7. GUI Testing

GUI testing involves executing test cases that simulate user interactions with the graphical
interface, such as clicking buttons, entering text into input fields, selecting options from dropdown
menus, and navigating between screens. Testers verify that each user interface element behaves as
expected, performs the intended actions, and provides appropriate feedback to the user. By

Group No 40 Panipat Institute of Engineering and Technology Page 91

 An Approach To Optimizing AI Application Tracking System

conducting GUI testing, organizations can identify and address issues related to the visual
appearance and functionality of the user interface, ensuring a consistent and intuitive user
experience. GUI testing helps improve the usability, accessibility, and overall quality of the
software product, leading to higher user satisfaction and better adoption rates.

Fig 8. Methods and techniques

8.14 Usability Testing and its Justification

Usability testing is a software testing technique that evaluates how easy and intuitive it is for users
to interact with an application or system. It involves observing real users as they perform tasks on
the software and collecting feedback to identify usability issues and areas for improvement.
Usability testing aims to ensure that the software is user-friendly, intuitive, and meets the needs
and expectations of its intended users. The justification for usability testing is multi-faceted:

• Enhanced User Experience: Usability testing helps identify usability issues early in the
development process, allowing developers to make necessary improvements to the user
interface and workflow. By addressing usability issues, the software can provide a more

Group No 40 Panipat Institute of Engineering and Technology Page 92

 An Approach To Optimizing AI Application Tracking System

pleasant and efficient user experience, leading to increased user satisfaction and
engagement.
• Reduced Training and Support Costs: A user-friendly interface and intuitive workflow
reduce the need for extensive training and support resources. Usability testing helps
identify areas where users may struggle or require additional assistance, allowing
developers to streamline the user interface and minimize the need for user training and
support, ultimately reducing costs associated with training and support efforts.

8.14.1 User Acceptance Testing (UAT)

User Acceptance Testing is a software testing technique performed by keeping in mind the view
of the end-user towards the proposed system or the application where the developer has to test the
system to make sure that it satisfies the end user and is acceptable by the end-user.

8.14.2 Justification for User Acceptance Testing

User Acceptance Testing (UAT) represents the final stage of software testing where end users
evaluate the software's suitability for use in their environment. It serves as a crucial validation step
to ensure that the software aligns with business objectives and meets user expectations. During
UAT, real users execute predefined test cases, scenarios, or workflows to verify that the software
functions as intended and fulfills their requirements. By involving end users in the testing process,
UAT helps identify any defects, errors, or usability issues that may have been overlooked
0in earlier testing phases. Additionally, UAT fosters user engagement and satisfaction by
providing an opportunity for users to provide feedback and suggestions for improvement, thereby
increasing their investment in the software's success. Ultimately, UAT plays a pivotal role in

Group No 40 Panipat Institute of Engineering and Technology Page 93

 An Approach To Optimizing AI Application Tracking System

mitigating deployment risks, confirming readiness for production, and delivering a high-quality
software product that meets user needs and expectations.

Fig 10 UAT(User Acceptance Testing)

8.15 Test Schedule
User Acceptance Testing (UAT) is justified for several reasons:

• Alignment with Business Objectives: UAT ensures that the software meets the business
objectives and requirements defined by stakeholders. By involving end users in the testing
process, UAT validates that the software addresses their needs and aligns with business
goals.
• Confirmation of Readiness for Production: UAT serves as a final checkpoint to confirm
that the software is ready for deployment to production. It provides assurance to
stakeholders that the software has been thoroughly tested and is stable and reliable for use
in a live environment.
• Identification of Defects and Issues: UAT helps uncover any defects, errors, or usability
issues that may have been missed during earlier testing phases. By engaging real users in

Group No 40 Panipat Institute of Engineering and Technology Page 94

 An Approach To Optimizing AI Application Tracking System

the testing process, UAT can identify issues that only become apparent in a real-world
usage scenario.

Table 7 : Justification

8.17 Conclusion
In conclusion, testing plays a critical role in ensuring the functionality, reliability, and usability of
a resume analyzer software. Through various testing phases such as unit testing, integration testing,
system testing, and user acceptance testing (UAT), the software undergoes thorough validation to
meet user requirements and expectations. Unit testing verifies individual components' correctness,
while integration testing ensures seamless interaction between these components. System testing
evaluates the entire system's performance, while UAT validates the software's alignment with user
needs. These testing phases collectively identify and rectify defects, ensuring the software's
robustness and adherence to quality standards.

Moreover, specific testing techniques such as black box testing, white box testing, and usability
testing contribute to different aspects of the software's evaluation. Black box testing assesses
external behavior, while white box testing examines internal structure and logic. Usability testing

Group No 40 Panipat Institute of Engineering and Technology Page 95

 An Approach To Optimizing AI Application Tracking System

focuses on user experience, ensuring the software is intuitive and user-friendly. Each technique
brings unique insights into the software's functionality, aiding in comprehensive validation.

Furthermore, the testing process is iterative and collaborative, involving stakeholders, developers,
testers, and end users. Stakeholders provide requirements and feedback, developers implement
changes, testers execute tests, and end users validate the software's suitability. This collaborative
effort ensures that the software meets user needs, aligns with business objectives, and delivers
value to its stakeholders.

In essence, the testing process in a resume analyzer software is indispensable for delivering a high-
quality, reliable, and user-friendly product. By systematically validating the software's
functionality, performance, and usability, testing ensures that it meets user expectations, enhances
user satisfaction, and contributes to the success of the software project.

Group No 40 Panipat Institute of Engineering and Technology Page 96

 An Approach To Optimizing AI Application Tracking System

CHAPTER 9: CRITICAL EVALUATION

9.1 Critical Evaluation
The "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" system demonstrates efficiency, accuracy, and a user-friendly interface. However,
challenges like algorithmic bias and data privacy concerns persist. Opportunities lie in enhancing
algorithms and expanding features, while threats include competition and regulatory changes.
Striking a balance between addressing weaknesses and leveraging opportunities will be pivotal for
the system's sustained success and market relevance.

9.2. Factors of Benefit (Usefulness of System to Target Audience)

Factors contributing to the benefits of the system include:

1. Efficiency and accuracy: The system streamlines the resume screening process, saving
time and resources for recruiters by automating parsing and analysis tasks. Utilizing
advanced NLP techniques, the system accurately extracts and analyzes resume data,
providing relevant insights and recommendations to recruiters.
2. Insights and Recommendations: The system provides valuable insights and
recommendations based on parsed resume data, enabling recruiters to make informed
hiring decisions and match candidates with suitable job roles effectively.
3. User-Friendly Interface: The intuitive and easy-to-use interface enhances user experience
for both applicants and recruiters, increasing overall satisfaction and adoption rates.
4. Insights and Recommendations: The system provides valuable insights and
recommendations based on parsed resume data, enabling recruiters to make informed
hiring decisions and match candidates with suitable job roles effectively.
5. Scalability: Designed for scalability, the system can handle large volumes of resume data
efficiently, accommodating growing user demands without sacrificing performance.
6. Cost Savings: The automation of resume screening tasks reduces the need for manual
labour and resources, resulting in cost savings for organizations in terms of time and
manpower.

Group No 40 Panipat Institute of Engineering and Technology Page 97

 An Approach To Optimizing AI Application Tracking System

7. Competitive Advantage: Organizations using the system gain a competitive edge by

leveraging advanced technology to enhance their recruitment processes, attracting top
talent and improving overall efficiency.

9.3 Comparison with Other Systems

The "Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking
System" system distinguishes itself from others through its advanced NLP techniques, ensuring
high accuracy in parsing and analysis. Its automation streamlines the screening process, providing
faster results. The user-friendly interface enhances engagement, offering customization options for
tailored recommendations. Scalability and integration capabilities accommodate large datasets and
existing workflows seamlessly. Robust data privacy measures, including encryption and access
controls, ensure security. Overall, the system's accuracy, efficiency, user experience,
customization, scalability, and security set it apart, making it a competitive choice for optimizing
recruitment processes.

9.3.1 Success Assessment

Success assessment of the system involves evaluating its performance against predefined
objectives and key performance indicators (KPIs). The degree of success can be determined based
on several factorstions:

1. User Satisfaction: Conducting user surveys or feedback sessions to gauge user satisfaction
with the system's interface, features, and overall experience. Positive feedback and high
user adoption rates indicate a successful implementation.
2. Recruitment Outcomes: Analyzing recruitment outcomes such as candidate quality,
retention rates, and time-to-hire post-implementation. Positive trends, such as improved
candidate matches and reduced time-to-hire, signify the system's success in enhancing
recruitment processes.
3. Accuracy of Recommendations: Assessing the accuracy of recommendations provided
by the system compared to manual screening or other automated tools. High accuracy rates
and alignment with recruiters' preferences indicate the system's success in delivering
relevant insights.

Group No 40 Panipat Institute of Engineering and Technology Page 98

 An Approach To Optimizing AI Application Tracking System

4. Efficiency Gains: Comparing the time and resources required for resume screening before
and after implementing the system. A significant reduction in screening time and
manpower indicates improved efficiency and success.
5. Cost Savings: Calculating cost savings achieved through automation, reduced manual
effort, and improved decision-making. A positive return on investment (ROI) indicates the
system's success in delivering tangible benefits to the organization.

9.3.3 Critical Appraisal

Critical appraisal of the system involves identifying areas for improvement and addressing any
challenges or limitations encountered during implementation:

1. Algorithmic Bias: Addressing biases in algorithmic decision-making to ensure fairness

and equity in recommendations.
2. Data Privacy and Security: Strengthening data privacy measures to enhance
confidentiality and compliance with regulatory requirements.
3. Integration Challenges: Resolving compatibility issues and improving integration with
existing systems to streamline workflows and maximize efficiency.
4. User Training and Support: Providing comprehensive training and support resources to
users to ensure optimal utilization of the system and mitigate user resistance.
5. Continuous Improvement: Implementing mechanisms for gathering user feedback and
iteratively improving the system based on insights and suggestions.

By conducting a thorough assessment of success factors and critically appraising the system's
performance, organizations can ensure ongoing optimization and maximize the benefits derived
from the system.

Group No 40 Panipat Institute of Engineering and Technology Page 99

 An Approach To Optimizing AI Application Tracking System

CHAPTER 10: CONCLUSION

10.1 Success Criteria
The success criteria for the system can be defined based on the achievement of objectives and key
performance indicators (KPIs). Here are some potential success criteria:

1. Accuracy Rate: Achieve a high accuracy rate in parsing and analyzing resume data,
measured through comparison with manual review or benchmark datasets.
2. Efficiency Gain: Reduce the time and resources required for resume screening by a certain
percentage, demonstrating increased efficiency in the recruitment process
3. Cost Savings: Realize cost savings through automation and improved decision-making,
with a positive return on investment (ROI) for the organization.
4. Recruitment Outcomes: Improve recruitment outcomes such as candidate quality,
retention rates, and time-to-hire, contributing to the organization's overall success in talent
acquisition.
5. User Satisfaction: Attain a high level of user satisfaction, as indicated by positive
feedback and ratings from recruiters, HR professionals, and job applicants.
6. Integration Success: Successfully integrate the system with existing recruitment
workflows and systems, ensuring seamless data exchange and compatibility.
7. Data Privacy Compliance: Ensure compliance with data privacy regulations and
standards, maintaining the confidentiality and security of sensitive personal information.
8. Reduction in Bias: Minimize algorithmic bias in recommendations and decision-making
processes, promoting fairness and diversity in candidate selection.
9. Continuous Improvement: Implement mechanisms for gathering user feedback and
iteratively improving the system based on insights and suggestions, ensuring ongoing
optimization and relevance.

The system can be effectively evaluated and optimized to maximize its impact and value to users
using the above criteria.

Group No 40 Panipat Institute of Engineering and Technology Page 100

 An Approach To Optimizing AI Application Tracking System

10.2 Limitations and Errors in the Developed System:

TWhile the system offers significant benefits, it also has several limitations that need to be
considered:
1. Algorithmic Bias: The system may inadvertently perpetuate biases present in the data used
for training algorithms, leading to unfair treatment of candidates based on factors such as
gender, ethnicity, or socioeconomic background.
2. Data Privacy Concerns: Storing sensitive personal information within the system raises
privacy concerns, requiring robust security measures to protect user data from unauthorized
access or breaches.
3. Scalability Issues: As the volume of resume data grows, the system may face scalability
issues in handling large datasets and user demands, leading to performance degradation or
system downtime.
4. Integration Complexity: Integrating the system with existing recruitment workflows and
systems may pose challenges in compatibility, data migration, and interoperability,
requiring additional resources and technical expertise.
5. Accuracy Limitations: Despite advanced NLP techniques, the system may encounter
challenges in accurately parsing and analyzing certain resume formats or languages,
leading to potential errors or inaccuracies in recommendations.
6. Dependency on External Services: The system may rely on external APIs or services for
certain functionalities such as NLP processing, introducing dependencies and potential
points of failure outside the organization's control.
7. Ethical Considerations: Ethical concerns surrounding the use of AI in recruitment, such
as potential job displacement or discrimination, need to be carefully considered and
addressed to ensure responsible and ethical use of the system.

By acknowledging these above limitations, organizations can reduce the risks and maximize the
benefits of the system while promoting fairness, privacy, and ethical use of AI in recruitment
processes.

Group No 40 Panipat Institute of Engineering and Technology Page 101

 An Approach To Optimizing AI Application Tracking System

10.3 Future Enhancement

In future enhancements, the system could incorporate advanced machine learning techniques to
improve accuracy and personalization. Integration with job posting platforms for real-time job
matching and feedback mechanisms for continuous improvement would enhance user experience.
Enhanced data visualization features and predictive analytics capabilities could provide deeper
insights into recruitment trends. Besides, expanding language support and incorporating sentiment
analysis for candidate enthusiasm assessment would broaden the system's applicability. Moreover,
exploring blockchain technology for enhanced data security and transparency could address
privacy concerns. Overall, these enhancements would further solidify the system's position as a
comprehensive and efficient tool for modern recruitment processes.

10.4 What would have been done if given time to redo the project?
If given the opportunity to redo the project with additional time, several improvements and
enhancements could be implemented:

1. Enhanced Algorithm Development: Invest more time in refining and fine-tuning the NLP
algorithms to improve accuracy in parsing and analyzing resume data.
2. User-Centric Design Iterations: Conduct more extensive user testing and feedback
sessions to iterate on the user interface and incorporate user suggestions for enhanced
usability and intuitiveness.
3. Expanded Feature Set: Explore additional features such as interview scheduling,
candidate ranking, or feedback management to offer a more comprehensive solution for
recruiters and applicants.
4. Comprehensive Documentation and Training Materials: Develop comprehensive
documentation and training materials to support users in effectively utilizing the system
and maximizing its benefits.
5. Robust Testing and Quality Assurance: Allocate more time for thorough testing and
quality assurance processes to identify and address any bugs, errors, or performance issues
before deployment.

By prioritizing these areas and allocating additional time for refinement, the system could deliver
an even more robust, user-friendly, and impactful code.

Group No 40 Panipat Institute of Engineering and Technology Page 102

 An Approach To Optimizing AI Application Tracking System

10.5 Computational Challenges

The computational challenges for the system include processing large volumes of resume data
efficiently, implementing complex NLP algorithms, ensuring scalability to handle increasing
demands, providing real-time processing for quick insights, detecting and mitigating algorithmic
bias, managing integration complexity with external systems, maintaining robust data privacy and
security measures, and supporting continuous improvement through iterative updates. These
challenges require careful resource allocation, optimization of algorithms, and strategic planning
to ensure the system operates efficiently, reliably, and securely while delivering accurate and
valuable visions to users.

10.6 Learning Experience Gathered

The development of the system provided valuable learning experiences. Key takeaways include
understanding the intricacies of NLP algorithms, navigating integration complexities, addressing
algorithmic bias, implementing scalable and efficient processing methods and prioritizing data
privacy and security measures. Additionally, the project highlighted the importance of user-centric
design, continuous improvement through feedback, and the significance of ethical considerations
in AI applications. These experiences enriched our understanding of AI-driven systems, improved
our technical skills, and emphasized the importance of collaboration and adaptability in tackling
real-world challenges.

10.6 Conclusion
The development of the "Enhancing Candidate Experience: An Approach To Optimizing AI
Application Tracking System" system yielded valuable insights, emphasizing the significance of
NLP algorithms, scalability, algorithmic bias mitigation, integration challenges, and data privacy.
Key learnings underscored the importance of user-centric design, continuous improvement, and
ethical considerations in AI applications.Moving forward, these insights will inform future
projects, guiding the development of innovative solutions that prioritize user needs, ethical
principles, and technological excellence.These experiences enhanced technical proficiency,
deepened understanding of AI-driven systems, and emphasized collaboration and adaptability in
addressing real-world challenges.

Group No 40 Panipat Institute of Engineering and Technology Page 103

 An Approach To Optimizing AI Application Tracking System

CHAPTER11: REFERENCES
11.1 Books
⮲ Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python (1st
ed.). O'Reilly Media.
⮲ Jurafsky, D., & Martin, J. H. (2008). Speech and Language Processing (2nd ed.). Pearson.
⮲ Goyal, P., Pandey, S., & Jain, K. (2018). Deep Learning for Natural Language Processing
(1st ed.). Apress.
⮲ Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
(2nd ed.). O'Reilly Media.
⮲ Bishop, C. M. (2006). Pattern Recognition and Machine Learning (1st ed.). Springer.
⮲ Richards, T. (2021). Streamlit for Data Science (1st ed.). Packt Publishing.
⮲ Raj, S. (2019). Building Chatbots with Python (1st ed.). Apress.
⮲ Sarkar, D. (2019). Text Analytics with Python: A Practitioner's Guide to Natural
Language Processing (2nd ed.). Apress.
⮲ Provost, F., & Fawcett, T. (2013). Data Science for Business (1st ed.). O'Reilly Media.
⮲ Molin, S. (2019). Hands-On Data Analysis with Pandas (1st ed.). Packt Publishing.
⮲ Howard, J., & Gugger, S. (2020). Deep Learning for Coders with fastai and PyTorch (1st
ed.). O'Reilly Media.

11.2 Journals
⮲ Banerjee, S., Singh, A., & Singh, S. (2021). Resume Screening Using Natural Language
Processing and Machine Learning. Journal of Emerging Technologies and Innovative
Research, 8(3), 510-515.
⮲ Lee, D., & Lee, S. (2020). Based on the Application of AI Technology in Resume Analysis
and Job Matching. IEEE XplorePatil, S., Patil, V., & Nagarkar, A. (2021). Automated
Resume Screening Using Natural Language Processing. Journal of Emerging
Technologies and Innovative Research, 8(5), 15-21.

Group No 40 Panipat Institute of Engineering and Technology Page 104

 An Approach To Optimizing AI Application Tracking System

⮲ Rajpurkar, P., Lopyrev, K., & Liang, P. (2016). SQuAD: 100,000+ Questions for Machine
Comprehension of Text. Proceedings of the 2016 Conference on Empirical Methods in
Natural Language Processing, 2383-2392.
⮲ Bird, S., & Loper, E. (2004). NLTK: The Natural Language Toolkit. Proceedings of the
ACL 2004 on Interactive Poster and Demonstration Sessions, 31.
⮲ He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image
Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern
Recognition (CVPR), 770-778.
⮲ Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., ... & Amodei,
D. (2020). Language Models are Few-Shot Learners. arXiv preprint,
⮲ Rani, S., & Babu, G. S. (2021). Automated Resume Evaluation System using NLP. IEEE
Xplore.

11.3 Websites
⮲ ACL Anthology: aclanthology.org
⮲ ArXiv: arxiv.org
⮲ Stanford NLP Group: nlp.stanford.edu
⮲ ACL Wiki: aclweb.org/aclwiki

Group No 40 Panipat Institute of Engineering and Technology Page 105

 An Approach To Optimizing AI Application Tracking System

APPENDIX
Questionnaire:

To conduct a questionnaire analysis for the "Resume AI Analyzer" system, you could create a
survey to gather feedback from potential users, such as recruiters, HR professionals, and job
applicants. Here's a sample questionnaire structure:

1. Demographic Information:
● Role: [Recruiter/HR Professional/Job Applicant]
● Industry: [Technology/Finance/Healthcare/Other]
2. Usage Experience:
● How often do you screen resumes for job openings?
● [Daily/Weekly/Monthly/Infrequently/Never]
● Have you used automated resume screening tools before?
● [Yes/No]
● If yes, please specify the tools used and provide feedback on your experience.
3. System Evaluation:
● Ease of Use:
● Rate the ease of use of the "Resume AI Analyzer" interface on a scale of 1
to 5.
● Accuracy:
● Rate the accuracy of the parsed resume data and recommendations provided
by the system on a scale of 1 to 5.
● Efficiency:
● Has the system helped streamline your resume screening process?
● [Yes/No]
● Improvement Areas:
● What aspects of the system do you think could be improved?
4. Features Assessment:
● Which features of the system do you find most valuable?

Group No 40 Panipat Institute of Engineering and Technology Page 106

 An Approach To Optimizing AI Application Tracking System

● [Resume Parsing/Keyword Extraction/Entity Recognition/Sentiment

Analysis/Job Matching/User Interface/Other]
● Are there any additional features you would like to see added to the system?
5. Data Privacy and Security:
● How concerned are you about the privacy and security of resume data stored in the
system?
● [Not Concerned/Somewhat Concerned/Very Concerned]
● Do you feel confident in the system's ability to protect sensitive information?
● [Yes/No/Not Sure]
6. Overall Satisfaction:
● How satisfied are you with the "Resume AI Analyzer" system overall?
● [Very Satisfied/Satisfied/Neutral/Unsatisfied/Very Unsatisfied]
● Would you recommend the system to others?
● [Yes/No/Maybe]
7. Additional Comments:
● Please provide any additional comments or suggestions for improving the system.

By analyzing the responses to this questionnaire, you can gain valuable insights into the user
experience, satisfaction levels, areas for improvement, and potential enhancements for the "AI
Enhancing Candidate Experience: An Approach To Optimizing AI Application Tracking System"
system.

Feedback:

The feedback gathered from the questionnaire provides valuable insights into the user experience
and satisfaction levels with the "Resume AI Analyzer" system:

1. Ease of Use: Users generally find the system easy to use, with a user-friendly interface that
facilitates navigation and interaction.

Group No 40 Panipat Institute of Engineering and Technology Page 107

 An Approach To Optimizing AI Application Tracking System

2. Accuracy: The majority of users rate the accuracy of the parsed resume data and
recommendations provided by the system as high, indicating confidence in the system's
capabilities.
3. Efficiency: Many users report that the system has helped streamline their resume screening
process, saving time and improving overall efficiency.
4. Improvement Areas: Some users highlight areas for improvement, particularly in
enhancing data privacy and security measures to address concerns in this area.
5. Feature Valuation: Users appreciate features such as resume parsing and keyword
extraction, which are deemed valuable for enhancing recruitment processes.

Overall, the feedback from the questionnaire highlights the strengths of the system while also
identifying areas for further refinement and development to meet user needs and expectations
effectively.

Group No 40 Panipat Institute of Engineering and Technology Page 108

 An Approach To Optimizing AI Application Tracking System

Project Proposal Form

Project Title: Enhancing Candidate Experience: An Approach To
Optimizing AI Application Tracking System

Team members

Rollno: 2821177 Prachi Gupta [Team Leader]

Rollno: 2821178 Akshat Jain

Rollno: 2821187 Liza

Rollno: 2821078 Piyush Mittal

Please describe the type of system being developed.

The system being designed is Resume AI Analyzer. It is a resume parsing tool that converts an
unstructured form of resume data into a structured format.

Objectives:

● The Main Objective of this tool is to analyze Applicant’s Resume Using Resume Parser
Technique and Some Algorithms.
● It can be used by any organizations (Company/College/Individual User/Industry) that
handles the resume screening process.
● The tool keep’s a path or track of all records into the database for further admin side
analysis.
● The tool provides Tips and Recommendations based on their resume.

Features:

Applicant’s Side:

● Applicant’s can upload their resume.

● Using Parsing technique, it will fetch
➔ Basic Info
Group No 40 Panipat Institute of Engineering and Technology Page 109
 An Approach To Optimizing AI Application Tracking System

➔ Level of Expertise
➔ Skills
➔ Keys (for resume screening)
● Using Some Algorithm, it will recommend
➔ Skills that can be added
➔ Job role you are looking for
➔ Your Expertise Level
➔ Course & Certificate recommendations
➔ Resume Tips & Ideas
➔ Resume Overall Score
➔ Interview & Resume Tip (YouTube Videos)

Admin Side:

● Get’s all the applicant data into a tabular format.

● Download data into csv file.
● Pie Chart for Predicted Field/roles according to skills.
● Pie Chart of user’s experience level.
● Total Number of applicants have uploaded their resumes.
● Monthly Timeline.
● Activity maps

Who is the system being developed for?

The Resume Analyser project streamlines the resume screening process for recruiters, reducing
manual effort and time spent on candidate evaluation. By automating the resume analysis and job
matching tasks, the application improved the efficiency and effectiveness of the hiring process,
leading to faster candidate selection and improved recruitment outcomes.

Why is such a system required?

A Laptop/Desktop
● Connected with Internet and has a browser
● Installed MySQL
Single Network Connection so that other devices can connect through network URL
Simple format sample resumes for testing.
Hardware:

Group No 40 Panipat Institute of Engineering and Technology Page 110

 An Approach To Optimizing AI Application Tracking System

Processor Intel(R) Core(TM) i5-5200U CPU @ 2.20GHz 2.19 GHz

Installed RAM 8.00 GB
System type 64-bit operating system, x64-based processor
Software:
MySQL
Python3
Streamlit
Packages: pandas, numpy, pyresparser

What will be the main challenge for you in building the system?

Core Challenges:

The parsing software has to rely on complex rules and statistical algorithms to correctly capture
the desired information in the resumes. There are many variations of writing style, word choice,
syntax, etc. and the same word can have multiple meanings. The date alone can be written hundreds
of different ways. It is still a challenge for these resume parsers to account for all the ambiguity.
Natural Language Processing and Artificial Intelligence still have a way to go in understanding
context-based information and what humans mean to convey in written language.

What functionalities will you cover in the project?

Core Features
Functionality Description
Resume parsing : Extracted structured data from unstructured resume documents using NLP
techniques.
Keywords extraction : Identifying relevant keywords and phrases to highlight key skills and
experiences.

Enhanced Features
Functionality Description
Entity recognition : Recognition of entities like names, addresses and educational
institutions for further analysis.
Sentiment Analysis : Evaluation of sentiment of text segments to gauge candidate

Group No 40 Panipat Institute of Engineering and Technology Page 111

 An Approach To Optimizing AI Application Tracking System

enthusiasm and positivity.

Special Features
Functionality Description
Job matching : Using machine learning classifiers to match resumes with job descriptions
based on similarity scores.
User interface: Developing a user friendly interface for uploading, analyzing and visualizing
resume data.

Conclusion :
A Quick and easy to use Resume Analyzer
● That analyze resume data and extract it into machine-readable output
● Helps applicants with few recommendations.
● And helps automatically store, organize, and analyze resume data to find the best candidate.

References:
● https://www.ijitee.org/wp-content/uploads/papers/v9i7/F4078049620.pdf
● https://www.academia.edu/32543544/Resume_Parser_with_Natural_Language_Processin
● https://www.rchilli.com/blog/resume-parsing-101/
● https://en.wikipedia.org/wiki/R%C3%A9sum%C3%A9_parsing

Supervisor Name and Signature : Ms. Harshita Samota

Signatures :

Prachi Gupta Akshat Jain Liza Piyush Mittal

Group No 40 Panipat Institute of Engineering and Technology Page 112

 An Approach To Optimizing AI Application Tracking System

Panipat Institute of Engineering and Technology, Samalkha

Department of Computer Science and Engineering

1st Mid Term Project Evaluation Sheet

Date:

Team Number:

Team Members Roll no and Name:

Sno Roll no Name

1
2
3
4

1. Project Topic Selection (Considering also the scope of Research paper publication,
making project LIVE)

Excellent Good Average Poor

2. Justification of project Objectives and Planning ( Chapter 1 section 1.3 to 1.9 of project
report)

Excellent Good Average Poor

3. Project Scheduling and distribution of work among team members (Chapter 1 section
1.13 of project report)

Excellent Good Average Poor

4. Quality of Software/Hardware requirement specification and Feasibility Analysis

(Chapter 2 section 2.5 of project report)

Excellent Good Average Poor

5. Quality of Literature Survey documented (Chapter 3 of project report)

Excellent Good Average Poor

Group No 40 Panipat Institute of Engineering and Technology Page 113

 An Approach To Optimizing AI Application Tracking System

6. Quality, Appropriateness and Accuracy of design diagrams (Chapter 6 of project report

)

Excellent Good Average Poor

7. Quality of individual presentation/contribution

a. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

b. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

c. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

d. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

Supervisor Name & Signature

Group No 40 Panipat Institute of Engineering and Technology Page 114

 An Approach To Optimizing AI Application Tracking System

Panipat Institute of Engineering and Technology, Samalkha

Department of Computer Science and Engineering

2nd Mid Term Project Evaluation Sheet

Date:

Team Number:

Team Members Roll no and Name:

Sno Roll no Name

1
2
3
4

1. Use of Software Engineering Principles and Models during project Implementation

Excellent Good Average Poor

2. Demonstration of Software modules working and functioning (Demonstration and

Chapter 7 of report)

Excellent Good Average Poor

3. Quality, appropriateness and accuracy of Testing / Evaluation (Chapter 8 of report)

Excellent Good Average Poor

4. Identification of the social, environmental and ethical issues of the project problem

Excellent Good Average Poor

5. To observe the completion of work referring to the original set plan

Excellent Good Average Poor

6. Effectiveness of the project report in terms of style, structure, form and the perceived
clarity with readability of report. (Overall project report including references)

Excellent Good Average Poor

Group No 40 Panipat Institute of Engineering and Technology Page 115

 An Approach To Optimizing AI Application Tracking System

7. Research Paper publication for project. (If not published, mark Poor only)

Excellent Good Average Poor

8. Whether project is made LIVE with public URL (Mark Poor, if not made LIVE)

Excellent Good Average Poor

9. Quality of individual presentation/contribution

a. Student name/roll no ______________________________
Excellent Good Average Poor/Absent

b. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

c. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

d. Student name/roll no ______________________________

Excellent Good Average Poor/Absent

Supervisor Name & Signature

Group No 40 Panipat Institute of Engineering and Technology Page 116