Employee Churn Analysis Project 📌 Project Overview Organizations often face challenges in retaining employees, leading to increased hiring and training costs. This project focuses on predicting employee churn using historical data and AutoML modeling with PyCaret. The insights can help HR teams proactively identify employees at risk and take preventive measures.

🎯 Problem Statement We are experiencing challenges with employee retention. The organization seeks to:

Identify employees who are likely to leave.

Take proactive measures to reduce churn.

Pilot Program:

Focused on new employees.

Built an Auto ML model trained on historical data to predict potential churners.

🛠 Project Agenda Build Database (BigQuery)

Created a centralized database to store historical employee data.

Connect Python to BigQuery (Colab)

Integrated Google Colab with BigQuery for seamless data extraction and analysis.

Build Churn Model (PyCaret - Auto ML)

Leveraged PyCaret to quickly experiment and find the best predictive model.

Key techniques: Classification models, Model Evaluation, Feature Importance.

Export Model Output to BigQuery

Predictions and processed data exported back for reporting and dashboarding.

Build Dashboard (Looker Studio)

Developed an interactive dashboard to monitor churn risk and employee insights.

Recommendations (PowerPoint / Google Slides)

Created a management-friendly report summarizing:

High-risk employees

Insights from the model

Suggested HR interventions

📊 Deliverables Employee Churn Dashboard in Looker Studio

AutoML Churn Prediction Model (PyCaret)

BigQuery database with historical & predicted data

Recommendation Presentation for management

⚙️ Tech Stack Data Storage: Google BigQuery

Data Analysis: Python, Pandas, PyCaret

Visualization: Looker Studio