• HR Employee Attrition Analysis • by Abdullah Bin Musa• HR Employee Attrition Analysis • by Abdullah Bin Musa

• HR Employee Attrition Analysis •

Portfolio project
Abdullah Bin Musa
• HR Employee Attrition Analysis
• •Overview Analyzed 1,470 employees from IBM HR dataset to identify key drivers of employee turnover. Built machine learning models and an interactive dashboard with actionable business recommendations.
•• Key Findings
"Overtime is the strongest risk factor" — employees working overtime are 3x more likely to leave (30.5% vs 10.4%)
"Sales Representatives" have the highest attrition at 39.8%
"Young employees (18-25)" show 34.8% attrition rate
"Income gap" — leavers earn $2,046 less per month on average
"Total annual cost" of attrition estimated at $20.4 million
•• Tools Used
Python (pandas, numpy, matplotlib, seaborn, scikit-learn)
Random Forest Classifier (87.8% accuracy)
Groq API (Llama 3.3 70B) for AI-generated insights
Lovable (interactive dark theme dashboard)
•• What's Included
Interactive dashboard with KPIs, charts, and filters
Feature importance analysis (top predictors: Monthly Income, Overtime, Age)
Financial impact calculation
AI-generated business recommendations
Full Python code in GitHub repository

0 likes · 0 views · May 23, 2026

• HR Employee Attrition Analysis • •Overview Analyzed 1,470 employees from IBM HR dataset to identify key drivers of employee turnover. Built machine learnin...

Tags