Employee Attrition Prediction

This project predicts employee attrition based on various workplace and personal factors. The model is built using Machine Learning techniques and deployed as an interactive Streamlit app.

🚀 Features

• Exploratory Data Analysis (EDA): Visualizing key factors influencing employee attrition.
• Feature Engineering: Created meaningful features using Best-fit Random Forest.
• Model Building: Implemented Voting Classifier, Bagging Classifier, and Random Forest.
• Hyperparameter Tuning: Used Optuna to optimize model performance.
• Employee Attrition Prediction App: Users can input details and get real-time predictions.

🎯 How to Use

1. Open the Streamlit App (link below).
2. Enter the required input details about an employee.
3. Click Predict Attrition to see whether the employee is likely to stay or leave.

📂 Dataset

The dataset contains key employee-related features, including:

• Age, Monthly Income, Distance from Home, Education Level, Number of Dependents, Company Tenure
• Remote Work, Leadership Opportunities, Company Reputation, etc.

The target variable is Attrition Status (Stay or Leave).

🔗 Live Demo

🚀 Check out the live app here: Employee Attrition Prediction