Internship Presentation

ENHANCING EMPLOYEE
RETENTION THROUGH HR
ANALYTICS:
A DATA-DRIVEN APPROACH

Presenter:
Atharva kambale
Pratik Kande
Mayur Khaire
lalit Aher
Date: 08/02/2025
Organization: Netleap IT Solutions
INTRODUCTION -

High Employee Turnover: Employee attrition is a

persistent issue in many organizations, leading to direct
costs (e.g., recruitment, training, onboarding) and indirect
costs (e.g., loss of knowledge, lower morale).
Central Challenge: To identify the key factors driving
employee turnover and how HR analytics can be used to
mitigate these challenges and enhance employee
retention.
Key Question: "What are the main factors influencing
employee attrition, and how can HR analytics help in
developing effective retention strategies?"
SIGNIFICANCE OF THE PROJECT
Data-Driven Decision-Making:
Shift from relying on intuition to making objective, data-driven decisions in HR practices.
Cost Savings:
Reducing turnover leads to significant cost savings related to recruitment, training, and
onboarding processes.
Employee Morale and Stability:
A stable workforce positively impacts team morale, productivity, and performance,
contributing to the overall organizational success.
Improved Retention:
By targeting the root causes of turnover with tailored retention strategies, organizations
can retain key employees, preserving institutional knowledge and reducing hiring costs.
MOTIVATION, SCOPE, AND RATIONALE
Motivation:
1. Financial Impact of Turnover:
Recruitment, onboarding, and training new employees are costly processes that
significantly impact the organization's budget. High turnover leads to recurring
expenses.
2. Competitive Advantage:
Talent retention is crucial for staying competitive, especially in industries where
skilled labor is in high demand. Retaining key employees ensures organizational
continuity and strengthens the workforce.
3. Embedding a Data-Driven Culture:
Traditional HR methods often rely on subjective feedback, but incorporating data
analytics helps HR teams make objective, evidence-backed decisions.
SCOPE AND RATIONALE :
Scope:
1. Data Coverage: The study covers employee demographics (e.g., age, gender, tenure), job-
related data (e.g., department, salary, job role), and performance metrics (e.g., promotion
history, job satisfaction).
2. Time Period: The analysis covers 2-3 years of historical data, ensuring that trends reflect current
workforce dynamics.
Rationale:
1. Enhancing Organizational Stability: Addressing turnover drivers can help stabilize teams and
maintain performance consistency.
2. Improving Employee Experience: By analyzing attrition factors (e.g., workload, career
opportunities), HR can improve job satisfaction, work-life balance, and employee engagement.
3. Future-Ready HR Function: Using HR analytics to anticipate turnover trends can help the
organization plan for future workforce needs.
DATA COLLECTION & METHODOLOGY
1. HR Information System (HRIS):
Captures employee demographic data (age, gender, department, education level) and job-
related data (salary, tenure, position).
Power BI Application: HRIS data will be imported directly into Power BI for dashboard
visualization (e.g., demographic breakdown, tenure distribution).
2. Performance Management System:
Includes performance reviews, ratings, promotion history, and employee feedback.
Power BI Application: Performance data can be linked to HRIS data for a comprehensive
view of employee performance trends across departments.
3. Exit Interviews and Surveys:
Qualitative data capturing reasons for leaving, which provides insights into personal
motivations (e.g., work-life balance, career growth, salary).
Power BI Application: Convert qualitative responses into categorical data (e.g., "salary,"
"career growth," "work environment") for trend analysis in Power BI.
DATA PREPROCESSING
1. Data Quality Checks
Remove Duplicates: Use Power Query to remove duplicate
employee records.
Reconcile Conflicting Records: Standardize data (e.g., salary,
tenure) using Power Query transformations.
Standardize Naming: Ensure consistent department and job titles
using Power Query’s “Replace Values.”
2. Handling Missing Values
Imputation: Fill missing values with mean/median (e.g., for salary
or tenure) using Power Query.
Exclusion: Remove records with critical missing data (e.g., exit
reasons) from the dataset.
3. Variable Transformation
Categorization: Group data into categories (e.g., salary bands, age
brackets) using calculated columns in Power BI.
Age/Tenure Brackets: Use DAX to create groups like "Under 2
years," "2-5 years," etc.
ANALYTICAL TECHNIQUES
1. Descriptive Analytics
Summarizing Data:
Description: Descriptive analytics is used to summarize the key
characteristics of the dataset. Examples include calculating the
average salary or median tenure of employees.
Power BI Application: Create DAX measures to compute
average, median, and mode for key variables (e.g., Average
Tenure, Median Salary).
Example - DAX measure for average salary
AverageSalary = AVERAGE(Employee[Salary])
Visualization:
Description: Use Power BI charts to visually summarize data
and trends.
Power BI Application: Visualize demographic distributions (e.g.,
number of employees per department) or turnover rates over
time using Power BI’s bar charts, line charts, and pie charts.
RESULTS-
Key Findings:
1. Departments with High Turnover : Certain departments, especially entry-level and
customer-facing roles, had higher turnover.
2. Top Attrition Drivers:
Salary: Employees who felt underpaid were more likely to leave.
Career Growth: Lack of growth opportunities and clear career paths was a
significant reason for turnover.
Work Environment: Poor relationships with management and company culture
contributed to attrition.
3. Vulnerable Demographics:
Young Employees: Employees aged 25-35 showed the highest turnover,
particularly in junior roles.
Short Tenure: Employees with 1–3 years of tenure were more likely to leave.
CONCLUSION & FUTURE STEPS -
Conclusion:
Summary: The analysis revealed that salary, career development, and management
relationships are key drivers of employee turnover.
Impact: By addressing these issues, the organization can reduce turnover and save
costs while improving overall employee morale and performance.
Future Steps:
1. Predictive Analytics: Implement predictive models to proactively address turnover.
2. Continuous Monitoring: Regularly update the dashboard with new data and trends
to stay ahead of attrition.
3. Stay Interviews: Conduct stay interviews to gather insights from employees who are
staying, to further improve retention efforts.
THANK
YOU!