TECHNICAL

SEMINAR Date :7/05/2025

Title :AI Resume analyser

Domain of Title: Artificial Intelligence and
Natural Language Processing in Recruitment

Under the guidance of:

USN :1CR22AD11 Guide
2
NAME :SUPREETH name:
K MURTHY GELUVARAJ
Designation:Assistant
professor
Department of Artificial Intelligence and Data
 2

Agenda
Introduction
Problem
Statement
Survey of Technologies
Methodology Used
System Architecture
Impact on Environment
Impact on Society
Domain-Specific Impact
Conclusion
References
 3
Introduction

Hiring is a crucial process for any organization, but manual resume screening is
slow and inefficient.
Human recruiters often deal with hundreds of resumes for a single job posting.
Manual evaluation is prone to human error and unconscious bias.
There’s a need for automation to ensure faster and fairer recruitment.
AI Resume Analyser uses Artificial Intelligence and Natural Language Processing
to screen and rank resumes automatically.
The system compares resumes with job descriptions to shortlist the most
relevant candidates.
 3

Problem statement
HR departments receive hundreds of resumes for each job opening.
Manually reviewing resumes is time-consuming, repetitive, and inconsistent.
There’s a risk of overlooking qualified candidates due to human fatigue or bias.
Small startups and large companies alike lack scalable resume screening
systems. Recruiters may not always match the right skills with job requirements
accurately.
There is a clear need for a systematic, unbiased, and scalable resume
screening solution.
 4
Survey of Technologies

Natural Language Processing (NLP): Used to parse resumes and

extract text-based features.
Named Entity Recognition (NER): Identifies names, skills,
degrees, organizations.
TF-IDF (Term Frequency-Inverse Document Frequency): Helps in giving
weight to keywords in resumes.
Support Vector Machine (SVM): A classification model tested in the
paper.
Random Forest Classifier: Evaluated for predicting candidate
suitability.
XGBoost: Gradient boosting model used for best results.
Sklearn and Pandas: For preprocessing and model development.
 6
Highlights of Technology/Methodology used in
the Selected Paper
Step 1: Input Collection
User uploads a resume (PDF) and job description.
Step 2: Resume Parsing
Extract text from the resume using a PDF parser (like pdfminer or
PyPDF2).
step 3: NLP Processing
Use Spacy to identify key information like name, skills, experience,
education.
step 4:Matching & Scoring
Compare extracted resume data with job description using:
Keyword matching
Weight-based scoring (e.g., skills 40%, experience 30%, education
30%)
 7

Highlights of Technology/Methodology used in

the Selected Paper

Step 5: Output
System displays match percentage and ranks resumes
accordingly.
 7

Highlights of Technology/Methodology used in

the Selected Paper

The dataset was gathered from GitHub resume data.

Resumes were preprocessed, and skills were extracted using NLP techniques.
Each resume was matched with job descriptions.
Models used: SVM, Random Forest, XGBoost.
XGBoost gave highest accuracy: 88%
Output: System ranks resumes and assigns a suitability score to each.
 8
Impact on environment
While AI resume analyzers are primarily digital and software-based, here are
some indirect environmental impacts:
1)Reduction in paper usage:
Encourages digital resumes and job applications — saves trees and paper.
2)Lower energy footprint for physical HR operations:
Reduces need for printing, physical storage, and transport of documents.
3) Minor increase in server energy use:
Cloud-based AI systems require electricity, but impact is small compared to
physical hiring processes.
 8
Impact on society
1)Faster Hiring Process:
Reduces unemployment gaps by speeding up candidate selection.
2)Fair and Unbiased Screening:
Reduces human bias (gender, ethnicity, etc.) in the initial shortlisting
stage.
3) Empowers Startups:
Small businesses can use AI-based solutions to recruit efficiently without a
large HR team.
4) Potential Job Displacement:
May reduce demand for manual screening jobs in HR (but increases need
for AI- skilled professionals).
 8
Impact on domain
1)Automates Repetitive Tasks:
Frees up HR professionals for more strategic roles like interviews and
culture- building.
2)Increases Accuracy:
Ensures that candidates are selected based on skill-job match, not
personal preference.
3) Improves Candidate Experience:
Faster responses and clear feedback through automated systems.
4) Standardized Evaluation:
Same criteria applied to all candidates ensures consistency.
 9
Conclusion

AI Resume Analyser is an efficient and intelligent solution to modern

hiring challenges.
It leverages NLP and Machine Learning to automate the screening
process.
Saves time, reduces bias, and improves the accuracy of resume-job
matching.
Beneficial for both large corporations and startups.
Represents a shift toward smarter, data-driven HR practices.
 1
References 0

1 Paper: AI Resume Analyzer Using Machine Learning Algorithms, IJERT,

Volume 11, Issue 9, Sept 2022
2 Scikit-learn Documentation – https://scikit-learn.org
3 XGBoost Documentation – https://xgboost.readthedocs.io
AI Resume Analyzer (Automated System)-https://www.ijaresm.com/ai-
resume- analyzer-automated-system
AI Resume Parser-https://github.com/insightfinder/ResumeParser
 11

THANK
YOU