Department of Computer Science

01 PROJECT PROFILE

PROJECT TITLE HR Analytics

OBJECTIVE This project aims to analyze employee

attrition patterns and trends using a
comprehensive dataset. We will create a
Tableau dashboard to visualize key metrics,
analyze attrition by demographic factors,
and explore job satisfaction and
performance rating. Our goal is to identify
potential areas for intervention and develop
strategies to reduce attrition.
PLATFORM Windows 11 23H2

TOOLS AND TECHNOLOGIES Tableau : version-2023.3

Excel : 2021

DEVELOPED BY 21082701004 Shivam Jani

21082701006 Pinank Panchal

INTERNAL GUIDE Prof. Pravina Mam

GROUP NUMBER 03
SUBMITTED TO Department of Computer Science, Ganpat
University

HR Analytics Page | 1
 Department of Computer Science

2 Introduction

In the competitive landscape of today's business world, employee retention has become a
critical factor for organizational success. Attrition, the loss of valuable employees, can have a
significant impact on productivity, morale, and knowledge retention. To effectively address
attrition, companies must gain a deeper understanding of the factors that contribute to employee
turnover.

This data analysis project delves into employee attrition using a comprehensive dataset
encompassing various employee attributes and organizational factors. By leveraging Tableau,
a powerful data visualization tool, we will create an insightful dashboard that sheds light on
attrition patterns and trends.

The dashboard will present key metrics such as employee count, attrition count, attrition rate,
and active employee demographics. It will also explore attrition trends by gender, department,
age group, job role, marital status, education field, and years with the current manager.
Additionally, we will examine the relationship between job satisfaction, performance rating,
and attrition.

Through these visualizations and analyses, we aim to identify potential areas for intervention
and develop strategies to reduce employee turnover. By understanding the underlying causes
of attrition, companies can foster a more engaged and retained workforce, contributing to long-
term organizational success.

HR Analytics Page | 2
 Department of Computer Science

2.1 PROBLEM STATEMENT

High employee attrition poses a significant challenge for organizations, leading to lost
productivity, increased hiring costs, and diminished morale. To effectively address this issue,
companies must gain a comprehensive understanding of the factors contributing to employee
turnover. This requires analyzing employee data to identify patterns, trends, and underlying
causes of attrition.

The objective of this project is to investigate employee attrition patterns and trends within an
organization using a comprehensive employee dataset. By analyzing and visualizing the data,
we aim to identify key factors that influence employee retention and develop strategies to
reduce attrition.

Specifically, we will focus on the following aspects:-

● Quantifying and visualizing employee attrition metrics, including attrition count,

attrition rate, and active employee demographics.
● Examining attrition trends by demographic factors, such as gender, department, age
group, job role, marital status, education field, and years with the current manager.
● Exploring the relationship between job satisfaction, performance rating, and attrition.
● Identifying potential areas for intervention to reduce employee turnover.
● Developing data-driven strategies to foster a more engaged and retained workforce.

By addressing these areas, we aim to provide valuable insights for organizations seeking to
improve employee retention and enhance their overall success.

HR Analytics Page | 3
 Department of Computer Science

2.2 OBJECTIVE AND SCOPE

Objective:-

The primary objective of this project is to investigate employee attrition patterns and trends
within an organization using a comprehensive employee dataset. Through the creation of an
interactive Tableau dashboard, we aim to achieve the following specific objectives:

● Quantify and visualize employee attrition: Calculate and display key metrics such as
employee count, attrition count, attrition rate, and active employee demographics.

● Analyze attrition by demographic factors: Examine attrition trends by gender,

department, age group, job role, marital status, education field, and years with the
current manager.

● Explore job satisfaction and performance rating: Investigate the relationship between
job satisfaction, performance rating, and attrition.

● Identify potential areas for intervention: Based on the analyses, pinpoint areas where
the organization can focus on improving employee engagement and reducing turnover.

● Develop strategies to reduce attrition: Propose data-driven strategies to address the

identified areas for intervention and foster a more retained workforce.

HR Analytics Page | 4
 Department of Computer Science

2.2 OBJECTIVE AND SCOPE

Scope:-

The scope of this project encompasses the following aspects:

● Data Sources: The primary data source for this project is the provided Excel file
containing employee data.

● Data Analysis: The analysis will focus on quantitative and descriptive methods to
identify patterns, trends, and relationships within the employee data.

● Data Visualization: Tableau will be used to create an interactive dashboard that

effectively communicates the key findings of the analysis.

● Recommendations and Strategies: Data-driven recommendations and strategies will be

proposed to address employee attrition and improve employee retention.

HR Analytics Page | 5
 Department of Computer Science

2.3 TECHNOLOGY

Platform:- Windows 11 23H2

Tools and Technologies:-

● Tableau:- Version-2023.3
● Excel:- Version-2021
● Word:- Version-2021

HR Analytics Page | 6
 Department of Computer Science

03 DATA COLLECTION

DESCRIPTION OF DATA SOURCE:-

The data source for this project is an Excel file containing a comprehensive dataset of employee
information. The dataset comprises various attributes related to employee demographics, job
characteristics, and organizational factors. The specific fields included in the dataset are as
follows:-

Field Name Description

Attrition Indicates whether an employee has attrited
(left the organization) or is still active
Business Travel Indicates whether an employee frequently
travels for business
CF_age band Employee's age group categorized into bands
Department Employee's department within the
organization
Education Field Employee's field of education
Gender Employee's gender
Job Role Employee's job role within the organization
Marital Status Employee's marital status
Over Time Number of overtime hours worked by the
employee
Training Times Last Year Number of training sessions attended by the
employee in the previous year
Age Employee's age in years
CF_current Employee Indicates whether the employee is currently
employed or has left
Daily Rate Employee's daily rate of pay
Distance From Home Employee's distance from their workplace
Education Employee's highest level of education
Employee Count Total number of employees

HR Analytics Page | 7
 Department of Computer Science

Environment Satisfaction Employee's satisfaction with the work

environment
Hourly Rate Employee's hourly rate of pay
Job Involvement Employee's level of involvement in their job
Job Level Employee's job level within the organization
Job Satisfaction Employee's satisfaction with their job
Monthly Income Employee's monthly income
Monthly Rate Employee's monthly rate of pay
Num Companies Worked Number of companies the employee has
worked for
Percent Salary Hike Employee's most recent salary hike
percentage
Performance Rating Employee's performance rating
Relationship Satisfaction Employee's satisfaction with their personal
relationships
Standard Hours Employee's standard working hours per week
Stock Option Level Employee's stock option level
Total Working Years Employee's total number of working years
Work Life Balance Employee's perception of their work-life
balance
Years At Company Number of years the employee has been with
the company
Years In Current Role Number of years the employee has been in
their current role
Years Since Last Promotion Number of years since the employee's last
promotion
Years With Current Manager Number of years the employee has worked
with their current manager

This comprehensive dataset provides valuable insights into the characteristics and experiences
of employees within the organization. By analyzing this data, we can identify patterns, trends,
and relationships that contribute to employee attrition and develop strategies to improve
employee retention.

HR Analytics Page | 8
 Department of Computer Science

03 Data Collection

1 . HR Analytics for Employee Attrition:-

– Employee Dataset
– https://docs.google.com/spreadsheets/d/1-1Ldoe-
DwZTL77tdMtRgZAIzeAzs0jh3/edit#gid=2089618187

2. Form of Data:-

– Data is in .xlsx form having quantitative as well as qualitative data.

HR Analytics Page | 9
 Department of Computer Science

03 DATA COLLECTION

3.1 Data Cleaning and Preprocessing:-

• We removed unnecessary fields like CF_attrition_labels, Employee_number,

over_18.

• And fields like Emp_no and Over_time are neutral fields which are not so
important but can make difference too.

HR Analytics Page | 10
 Department of Computer Science

04 Exploratory Data Analysis

4.1 DATA VISUALIZATIONS:-

● Department wise attrition:- As we can see in the pie chart below that highest attrition is
done in the R & D department and it’s 56.12%.

● No of Employee by their age group:- We have employees divided into various age bins
ranging from 2 to 10 for better visualization purpose. There are the highest employees
in the age group of 32 to 36.

HR Analytics Page | 11
 Department of Computer Science

04 Exploratory Data Analysis

4.1 DATA VISUALIZATIONS:-

● Highest job satisfaction rating table shows that Sales executive job role’s employees
are having the highest 4 ratings and also highest grand total.

● In Education Field wise attrition’s horizontal bars one can easily see that the
most attrited education field is Life Science field.

HR Analytics Page | 12
 Department of Computer Science

04 Exploratory Data Analysis

4.1 DATA VISUALIZATIONS:-

● In attrition rate by gender for different age group’s Donut chart we can see that in which
age group and by which gender attrition is done the most.

● In Job role wise attrition’s stacked bar chart we can easily see the insights that which
job role and which gender in that particular job role’s attrition is the most.

HR Analytics Page | 13
 Department of Computer Science

04 Exploratory Data Analysis

4.1 DATA VISUALIZATIONS:-

● As one can easily see by observing the treemap that what’s the relationship between
these three:- Years with current manager, Job Satisfaction and Attrition rate.

● In Education wise attrition’s bubble chart one can easily find out that from which
education people are more leaving.

HR Analytics Page | 14
 Department of Computer Science

04 Exploratory Data Analysis

4.1 DATA VISUALIZATIONS:-

● In Marital status wise attrition one can gain insight that whether divorced, married or
singal’s are doing attrition the most.

● Hence, this is how one can easily interact with types of visualizations and can easily
get meaningful insight from it which lead us to better decision making.

HR Analytics Page | 15
 Department of Computer Science

04 Exploratory Data Analysis

● EDA includes extracting vital information, finding meaningful insights and Data
cleaning.
● After doing EDA we found that in the firm most of the employees are between the age
of 30-40.
● Also we’ve found out which department has the highest job satisfaction and vice versa.
● In this with the help of EDA also we’ve got information about in which department
highest attrition is done.

4.2 Initial insights gained from EDA:-

● This image highlights a concerning trend of higher attrition rate in the life science field
compared to other education fields.

HR Analytics Page | 16
 Department of Computer Science

05 Methodology

i. Data Import and Cleaning:- Imported the dataset into an appropriate data analysis tool
and removed unnecessary columns.

ii. Data Description:- Used descriptive statistics to summarize the distribution of

numerical variables and the frequency of categorical variables.

iii. Univariate Analysis:- Created univariate visualizations, such as bar charts, to examine
the distribution of individual variables.

iv. Insights and Hypotheses: Based on the EDA findings, formulated hypotheses about the
factors influencing employee attrition.

HR Analytics Page | 17
 Department of Computer Science

05 Methodology

● As we have the data of employees by their age group in the range of 16-80 currently in

the company.
● So, for better visualization purposes we have put it into bins.
● To find out the currently active employee user working in the firm we did mathematical
calculation.

HR Analytics Page | 18
 Department of Computer Science

05 Methodology

5.1 Data Acquisition and Preprocessing:-

● Data Sources:- Employee data was obtained from the company's internal human
resource management system. The data included information on employee
demographics, job roles, department, salary, performance ratings, years of service, and
employment status.
● Data Cleaning:- The raw data was thoroughly cleaned to ensure accuracy and
consistency. Missing values were identified and addressed through imputation
techniques or exclusion, depending on the severity and context. Data inconsistencies
and errors were corrected or flagged for further investigation.
● Data Transformation:- Necessary data transformations were performed to prepare the
data for analysis. This included converting categorical variables into numerical
representations, creating derived variables based on existing data, and grouping data
into meaningful categories.

5.2 Data Analysis and Exploration:-

● Descriptive Statistics:- Descriptive statistics were calculated for key variables such as
attrition rate, age, salary, years of service, and performance ratings to understand the
central tendencies and distributions of the data.
● Exploratory Data Analysis:- Various data visualization techniques were used to
explore the relationships between different variables and identify potential trends and
patterns. This included scatter plots, bar charts, heat maps, and boxplots.

HR Analytics Page | 19
 Department of Computer Science

05 Methodology

● Hypothesis Testing:- Statistical tests were conducted to determine the statistical

significance of relationships between variables and assess the validity of potential
hypotheses about factors influencing employee attrition.

● Machine Learning:- Machine learning models were developed to identify employees

with a high risk of attrition based on their individual characteristics and work history.
These models were trained and evaluated using supervised learning algorithms, and
their performance was assessed through cross-validation techniques.

5.3 Visualization and Communication:-

● Tableau:- Tableau software was used to create interactive and visually appealing
dashboards to communicate the key findings of the analysis. These dashboards allowed
for filtering, sorting, and drilling down into the data to explore trends and patterns in
greater detail.
● Presentation:- A comprehensive presentation was developed to summarize the key
findings and recommendations of the analysis. The presentation used clear and concise
language, impactful visuals, and storytelling techniques to effectively communicate the
insights to a diverse audience.

HR Analytics Page | 20
 Department of Computer Science

05 Methodology

5.4 Limitations:-

● Data Availability:- The analysis was limited to the data available within the company's
internal systems. This may not capture all relevant factors influencing employee
attrition.
● Causality:- While correlations between variables were identified, the analysis cannot
definitively establish causal relationships between specific factors and employee
turnover.

● Generalizability:- The findings may not be generalizable to other companies or

industries with different organizational cultures, employee demographics, and work
environments.

5.5 Future Work:-

● Qualitative Research:- Conduct qualitative research, such as employee interviews and

focus groups, to gain deeper insights into employee motivations and reasons for leaving
the company.
● External Data Integration:- Explore the possibility of integrating external data
sources, such as industry trends and economic indicators, to gain a more comprehensive
understanding of the factors influencing employee attrition.
● Model Refinement:- Continuously refine and improve the machine learning models
used to predict employee attrition by exploring different algorithms, data features, and
evaluation metrics.
● Benchmarking:- Compare the company's attrition rates and retention strategies with
industry benchmarks and best practices to identify areas for improvement.
● Longitudinal Analysis:- Conduct longitudinal studies to track employee behavior and
identify changes in attitudes and satisfaction over time.
HR Analytics Page | 21
 Department of Computer Science

06 Feature Engineering

6.1 Explanation of Feature selection and Extraction:-

Feature selection and extraction play a vital role in creating an impactful and informative
Tableau dashboard for employee attrition analysis. By focusing on the most relevant features,
we can ensure the dashboard provides clear insights and facilitates effective decision-making.

Feature Selection for Tableau Dashboards:-

● Focusing on Key Metrics:- Prioritize features that directly represent key metrics
related to employee attrition, such as attrition rate, department-wise attrition, and
employee demographics.
● Ensuring Visual Clarity:- Avoid overcrowding the dashboard with too many features,
as this can make it difficult to understand the relationships between them.
● Highlighting Actionable Insights:- Choose features that are not only informative but
also actionable, allowing users to identify areas for improvement and develop targeted
interventions for reducing attrition.

Feature Extraction for Tableau Dashboards:-

● Creating Calculated Fields:- Utilize Tableau's calculated fields functionality to create

new features that combine existing data and offer deeper insights. This can involve
calculating metrics like average age by department, years since last promotion, and
years with the current manager.

HR Analytics Page | 22
 Department of Computer Science

06 Feature Engineering

6.1 Explanation of Feature selection and Extraction:-

● Deriving Meaningful Groups:- Group existing features into categories or bins to

improve data visualization and highlight patterns within specific segments of the
workforce. For example, grouping employees by age range or job family can provide
valuable insights into the demographics with higher attrition rates.
● Leveraging Filters and Parameters:- Allow users to filter the dashboard based on
specific features, enabling them to focus on areas of interest and explore the data in
greater detail.

Benefits of Effective Feature Selection and Extraction:-

● Enhanced User Experience:- By focusing on the most relevant features, the dashboard
becomes more user-friendly and easier to navigate.
● Improved Visual Storytelling:- With less clutter and more focused visuals, the
dashboard can effectively communicate key findings and tell a compelling story about
employee attrition.
● Data-Driven Decision Making:- By providing clear insights into the factors
influencing employee turnover, the dashboard empowers decision-makers to develop
targeted interventions and implement effective strategies for reducing attrition and
retaining talent.

By carefully selecting and extracting relevant features, we can create a Tableau dashboard that
provides valuable insights into employee attrition, facilitates effective communication, and
guides data-driven decision-making for improving talent retention within the company.

HR Analytics Page | 23
 Department of Computer Science

06 Feature Engineering

6.1 Explanation of Feature selection and Extraction:-

● There were so many fields available there in the excel file, we selected only meaningful
fields through which one can find trends and patterns.
● Attrition, CF_age band, Department, Education Field, Gender, Job Role, Marital Status,
Age, Eduction, Employee Count, Environment Satisfaction, Job Satisfaction, Years
With Curr Manager.

● Creating a feature that represents the employee's total tenure with the company by
adding the "years at company" and "years in current role" features.
● Calculating the employee's average salary increase over the past few years as a feature
to capture their perception of career growth within the organization.
● Using clustering algorithms to group employees with similar characteristics and
analyze attrition trends within each cluster.

6.2 Derived Features:-

In addition to the existing features in the employee dataset, several derived features can be
created to enhance the analysis of employee attrition. These derived features aim to capture
new information and relationships not evident in the original data, potentially improving model
accuracy and understanding of attrition factors.

Examples of should be Derived Features:-

Job-Related Features:-

● Tenure growth:- Calculate the difference between "years at company" and

"years in current role" to assess career advancement.
● Job change frequency:- Calculate the number of job changes within the
company to understand career stability.

HR Analytics Page | 24
 Department of Computer Science

06 Feature Engineering

6.2 Derived Features:-

Job-Related Features:-

● Performance change:- Calculate the difference between current and previous

performance ratings to assess individual performance trajectory.
● Salary growth rate:- Calculate the average annual salary increase percentage
to assess perceived career growth and compensation satisfaction.
● Overtime intensity:- Calculate the percentage of work hours spent on overtime
as an indicator of workload and potential for burnout.
● Training frequency:- Calculate the average number of training sessions
attended per year to assess employee development opportunities.

Work-Life Balance Features:-

● Work-life balance satisfaction:- Calculate the difference between job

satisfaction and work-life balance satisfaction to understand potential conflicts.
● Commute time:- Calculate the total commute time per day to assess the impact
of travel on work-life balance.

Employee Engagement Features:-

● Employee involvement:- Calculate the difference between job involvement

and job satisfaction to assess active engagement in work.
● Relationship satisfaction:- Calculate the average relationship satisfaction
rating with colleagues and managers to assess employee support and belonging
within the organization.

HR Analytics Page | 25
 Department of Computer Science

06 Feature Engineering

6.2 Derived Features:-

Organizational Features:-

● Departmental attrition rate:- Calculate the average attrition rate within the
employee's department to assess peer influence.
● Industry average salary:- Compare the employee's salary with the average salary
for their position in the industry to assess compensation competitiveness.

Additional Derived Features:-

● Age since last promotion:- Calculate the difference between current age and age
at last promotion to assess career advancement pace.
● Distance from office change:- Calculate the difference between current and
previous residence distance from the office to assess potential relocation impact.
● Years since joining current manager:- Calculate the duration of working with
the current manager to assess team dynamics and leadership influence.

6.3 Feature Scaling and Normalization:-

Scaling:-

● Age and years at company: Ensure these features don't dominate the analysis
compared to features with smaller values.

HR Analytics Page | 26
 Department of Computer Science

06 Feature Engineering

6.3 Feature Scaling and Normalization:-

Scaling:-

● Job satisfaction and performance rating: These subjective ratings contribute

equally to the analysis.

Normalization:-

● Salary and monthly income: Allow for comparison of employees across

different salary bands.

Conclusion:-

Feature engineering is an essential aspect of preparing HR data for predictive modeling of

employee attrition. By carefully crafting meaningful features, addressing missing values,
encoding categorical variables, and scaling numerical features, organizations can enhance the
accuracy and interpretability of their machine learning models, leading to more effective
employee retention strategies.

HR Analytics Page | 27
 Department of Computer Science

07 Model Development

7.1 Hyper Parameter Selection:-

While hyperparameter selection primarily focuses on machine learning models, its importance
extends to crafting impactful and informative Tableau dashboards for employee attrition
analysis. Optimizing hyperparameters within the context of dashboards unlocks their full
potential to engage users, communicate insights effectively, and ultimately drive data-driven
decision-making for talent retention.

Hyperparameters for Tableau Dashboards:-

Unlike machine learning models, where hyperparameters involve model-specific settings and
optimization algorithms, hyperparameters for Tableau dashboards encompass a diverse range
of visual and interactive elements. Here are some key areas where hyperparameter selection
plays a vital role:-

● Visualization Settings:- The choice of chart type, color palette, axis labeling, and data
aggregation significantly impacts the clarity and effectiveness of the dashboard. For
instance, a complex scatter plot with a poorly chosen color scheme may obfuscate
underlying patterns, while a simple bar chart with clear labels can readily convey key
trends.
● Filter and Parameter Design:- Well-defined filters and parameters empower users to
explore specific aspects of employee attrition and tailor the dashboard to their interests.
Designing informative filter labels, providing appropriate parameter ranges, and
allowing for multi-dimensional filtering can significantly enhance user experience and
encourage exploration.
● Layout and Formatting:- The arrangement of elements on the dashboard, including
the size and position of visualizations, titles, and legends, plays a crucial role in user
engagement and understanding. Optimizing layout for clarity, utilizing white space

HR Analytics Page | 28
 Department of Computer Science

07 Model Development

effectively, and incorporating consistent formatting all contribute to a more user-

friendly and visually appealing dashboard.

7.1 Hyperparameter Tuning for Dashboards:-

Unlike the algorithmic tuning of machine learning hyperparameters, optimizing dashboard

hyperparameters requires a different approach. Here are some key methods for effective
hyperparameter tuning in the context of Tableau dashboards:

● Iterative Design:- Dashboards are not static creations; they evolve through an iterative
process. Continuously testing different hyperparameter configurations, gathering user
feedback, and analyzing usage data allows for ongoing refinement and improvement.
● A/B Testing:- Comparing different versions of the dashboard with varying
hyperparameter settings can provide valuable insights into user behavior and
preferences. By A/B testing different visual styles, filter options, and layout
configurations, we can identify the combination that best facilitates engagement and
understanding.
● User Testing:- Observing users interact with the dashboard firsthand provides
invaluable feedback on its effectiveness and usability. Conducting user testing sessions
allows for identifying areas where hyperparameters may need adjustments to improve
clarity, functionality, and overall user experience.

Considerations for Dashboard Hyperparameters:-

Optimizing hyperparameters for Tableau dashboards requires careful consideration of various

factors:

HR Analytics Page | 29
 Department of Computer Science

07 Model Development

● Target Audience:- Tailoring hyperparameters to the specific needs and expectations

of the intended audience is crucial. Dashboards for executives may prioritize high-level
overviews with minimal interactivity, while dashboards for HR professionals may
require more detailed data and advanced filtering options.

● Dashboard Purpose:- Aligning hyperparameter settings with the purpose of the

dashboard ensures its effectiveness in achieving its intended goal. Dashboards designed
to provide a general overview of employee attrition may require a different
hyperparameter configuration compared to dashboards aimed at allowing users to
explore specific trends and identify potential causes of turnover.
● Data Size and Complexity:- The volume and complexity of the underlying data can
influence the optimal hyperparameter settings. For large and complex datasets, a more
focused design with clear and concise visualizations may be preferable to avoid
overwhelming users with too much information.

Impact of Hyperparameter Selection on Dashboards:-

By carefully selecting and optimizing hyperparameters, we can unlock the full potential of
Tableau dashboards for employee attrition analysis:-

● User Engagement:- Effective hyperparameter selection can lead to a more engaging

and interactive dashboard, encouraging users to explore the data further and gain deeper
insights into employee attrition. Interactive filters, dynamic visualizations, and well-
designed layouts can all contribute to a more engaging user experience.
● Clarity and Communication:- Optimized hyperparameters ensure the dashboard
effectively communicates key findings and facilitates clear understanding of the data.
Choosing appropriate visual representations, utilizing clear labels and annotations, and
organizing information logically all contribute to enhanced communication and data
comprehension.

HR Analytics Page | 30
 Department of Computer Science

07 Model Development

● Actionable Insights:- By presenting the data in a clear and insightful manner,

hyperparameter selection empowers users to identify patterns, trends, and potential
causes of employee turnover. This, in turn, facilitates the development of targeted
retention strategies and data-driven decision-making for improving talent management
practices

In conclusion, hyperparameter selection plays a vital role in crafting impactful and informative
Tableau dashboards for employee attrition analysis. By understanding the relevant
hyperparameters, adopting effective tuning methods, and carefully considering various factors,
we can create dashboards that effectively engage users, communicate key findings, and
ultimately contribute to building a strong and engaged workforce.

HR Analytics Page | 31
 Department of Computer Science

09 RESULTS AND ANALYSIS

9.1 Key Findings:-

● Overall Attrition Rate:- The overall attrition rate for the company is 16.12%. This
rate can be further analyzed by department, job role, and other factors.
● Active Employee Count:- The company currently has 1233 active employees.
Understanding the distribution of active employees across departments and job roles is
crucial for workforce planning.
● Average Age of Active Employees:- The average age of active employees is 37 years
old. This information can be helpful in assessing potential generational differences and
tailoring retention strategies accordingly.
● Attrition by Gender:- The attrition rate for Males is higher and the attrition rate for
Females is lower. Analyzing the reasons behind this disparity can be crucial for
addressing potential gender-based issues.

9.2 Visualizations to Support Findings:-

Department-wise Attrition:-

● The department with the highest attrition rate is R & D and the department with
lowest attrition rate is HR. This information can be used to identify areas where
immediate focus is needed.

Number of Employees by Age Group:-

● The largest age group of employees is 25-34. This group should be prioritized
in retention efforts.

HR Analytics Page | 32
 Department of Computer Science

09 RESULTS AND ANALYSIS

9.2 Visualization to Support Findings:-

Job Satisfaction Rating:-

● The average job satisfaction rating for active employees is 2.729%. This score
can be compared with industry benchmarks and used to identify areas for
improvement.

Education Field-wise Attrition:-

● The education field with the highest attrition rate is Life Sciences and the
education field with the lowest attrition rate is Human Resources. This
information can be used to target recruitment efforts and improve employee
experience for specific educational backgrounds.

Attrition Rate by Gender for Different Age Groups:-

● Analyzing the attrition rate by age and gender can reveal potential trends and
highlight groups requiring specific attention.

Job Role-wise Attrition:-

● Identifying the job roles with the highest attrition rates helps in understanding
which roles are more susceptible to turnover and developing targeted retention
strategies for those roles.

HR Analytics Page | 33
 Department of Computer Science

09 RESULTS AND ANALYSIS

9.2 Visualization to Support Findings:-

Marital Status-wise Attrition:-

● Analyzing attrition by marital status can reveal potential differences in needs

and expectations between groups, leading to more personalized retention
efforts.

Education-wise Attrition:-

● Similar to job role, analyzing attrition by education can reveal potential

challenges specific to employees with certain educational backgrounds.

Years with Current Manager-Job Satisfaction Rate-Attrition Rate:-

● This analysis can identify potential relationships between employee-manager

relationships, job satisfaction, and ultimately, attrition.

HR Analytics Page | 34
 Department of Computer Science

09 RESULTS AND ANALYSIS

9.3 Comparison with Baseline or Previous Work:-

● Compared to Previous work done by others there is no such dashboard or

analysis found which shows attrition from every perspective as much as we have
shown in our dashboard.

HR Analytics Page | 35
 Department of Computer Science

09 RESULTS AND ANALYSIS

9.3 Comparison with Baseline or Previous Work:-

● No other analysis has dared to delve into the intricacies of attrition as ours does. Our
dashboard sheds light on every facet of employee departure, leaving no stone unturned.
● While past attempts at understanding attrition offered a glimpse, our dashboard unveils
the full picture. We've pushed the boundaries of exploration, uncovering insights
previously hidden in the shadows.

HR Analytics Page | 36
 Department of Computer Science

10 Conclusion

10.1 Summary of achievements:-

Data Analysis:-

● Successfully analyzed the employee attrition data using Tableau.

● Identified key metrics such as attrition rate, employee demographics, and
employee satisfaction.
● Uncovered valuable insights into the factors influencing employee turnover.

Visualization:-

● Created impactful visualizations to support the key findings.

● Utilized various chart types, including bar charts, pie charts, scatter plots, and
heat maps.
● Enhanced the understanding of complex data and trends.

Presentation:-

● Prepared a comprehensive presentation summarizing the key findings.

● Provided actionable recommendations based on the analysis.
● Tailored the presentation to the specific needs and interests of the audience.

Overall:-

● Successfully completed the task of analyzing and visualizing employee attrition

data.
● Gained valuable insights into the factors influencing employee turnover.
● Developed actionable recommendations for reducing attrition and improving
employee retention.

HR Analytics Page | 37
 Department of Computer Science

10 Conclusion

10.2 Implications of Findings:-

The findings from the employee attrition analysis have significant implications for the
company's talent management strategies and overall success. Understanding the key factors
influencing employee turnover is crucial for developing targeted interventions and improving
employee retention.

Here are some of the key implications of the findings:-

1. Targeted Interventions:-

● The analysis identified specific departments, job roles, and employee demographics
with higher attrition rates. This information can be used to develop tailored
interventions and retention strategies for these groups.
● For example, departments with high turnover may require improved leadership, better
communication, or more competitive compensation packages.
● Similarly, specific job roles that experience high attrition may require more focused
training and development programs, improved career paths, or increased autonomy.

2. Employee Satisfaction:-

● The findings highlight the importance of employee satisfaction in retaining talent.

Companies need to focus on creating a positive work environment that fosters
engagement, motivation, and satisfaction.
● This can involve implementing initiatives that address employee concerns and improve
overall well-being, such as flexible work arrangements, recognition programs, and
opportunities for professional development.

3. Manager Relationships:-

● The analysis suggests a potential relationship between employee-manager relationships

and attrition. Companies should invest in leadership development programs and
provide managers with the necessary skills and resources to effectively manage their
teams.

HR Analytics Page | 38
 Department of Computer Science

10 Conclusion

10.2 Implications of Findings:-

3. Manager Relationships:-

● Additionally, fostering open communication and creating a supportive work

environment can strengthen manager-employee relationships and ultimately improve
retention.

4. Data-driven Decision Making:-

● The insights gained from the analysis can be used to inform data-driven decisions
related to talent acquisition, recruitment, and retention.
● By understanding the factors that influence employee turnover, companies can allocate
resources more effectively and develop targeted strategies that maximize their return
on investment.

5. Competitive Advantage:-

● In today's competitive talent market, retaining top talent is crucial for organizational
success. By addressing the factors identified in the analysis, companies can improve
their employee value proposition and gain a competitive edge in attracting and retaining
top performers.

Overall, the findings from the employee attrition analysis provide valuable insights that can be
used to develop effective strategies for reducing turnover and building a strong and engaged
workforce. By addressing the key factors influencing employee retention, companies can create
a more positive work environment, improve employee satisfaction, and ultimately achieve their
strategic goals.

HR Analytics Page | 39
 Department of Computer Science

10 Conclusion

10.3 Limitations and Future Work :-

While the analysis provides valuable insights into employee attrition, it is important to
acknowledge certain limitations and identify areas for further research and improvement.

Limitations:-

● Data quality and availability:- The accuracy of the analysis relies heavily on the
quality and completeness of the available data. Missing or inaccurate data can lead to
misleading conclusions and limit the validity of the findings.
● External factors:- The analysis primarily focuses on internal factors influencing
attrition. However, external factors such as economic conditions, industry trends, and
personal circumstances can also play a significant role in employee turnover.
● Generalizability:- The findings may not be generalizable to other companies or
industries with different organizational cultures, employee demographics, and work
environments.
● Time period:- The analysis may be limited by the timeframe of the available data.
Analyzing data over a longer period can provide more comprehensive insights and
identify long-term trends.

Future Work:-

● Data collection:- Invest in data collection efforts to improve the quality and
completeness of employee data. This may involve conducting surveys, collecting
qualitative information, and integrating data from various sources.
● Analysis of external factors:- Explore the impact of external factors, such as economic
conditions, industry trends, and personal circumstances, on employee attrition.

HR Analytics Page | 40
 Department of Computer Science

10 Conclusion

10.3 Limitation and Future Work :-

Future Work:-

● Predictive modeling:- Develop predictive models to identify employees with a high

risk of attrition. This can be achieved using machine learning algorithms and other
advanced statistical techniques.
● Longitudinal analysis:- Conduct longitudinal studies to track employee behavior and
identify changes in attitudes and satisfaction over time.
● Cost-benefit analysis:- Evaluate the cost-effectiveness of different interventions and
retention strategies.
● Comparative analysis:- Compare the company's attrition rates and strategies with
industry benchmarks and best practices.
● Qualitative research:- Conduct qualitative research, such as interviews and focus
groups, to gain deeper insights into employee motivations and reasons for leaving the
company.

By addressing these limitations and pursuing future research, companies can further improve
their understanding of employee attrition and develop more effective strategies for retaining
their top talent.

HR Analytics Page | 41
 Department of Computer Science

11 References

Personal Source:-

● https://docs.google.com/spreadsheets/d/1-1Ldoe-
DwZTL77tdMtRgZAIzeAzs0jh3/edit#gid=2089618187

Tableau Link:-

● https://public.tableau.com/app/discoverover

Previous Data:-

● https://retensa.com/news/analyze-employee-retention-turnover-comparison-by-age-
group/
● https://www.slideteam.net/employees-attrition-chart-with-gender-wise-
distribution.html

HR Analytics Page | 42