Employee Attrition Prediction using Random Forest

📌 Problem Statement

The goal of this project is to predict employee attrition in a firm using machine learning. Early detection of potential attrition helps HR teams plan manpower requirements and improve employee retention strategies.

---

📊 Dataset

• Dataset: Contains employee records with demographic, job-related, and performance features.
• Samples: 1471
• Features: Attrition and 34 more features0
• Target:
  • 1 → Employee will leave (attrition)
  • 0 → Employee will stay

---

⚙️ Approach

1. Data Preprocessing

• Handled categorical variables using Label Encoding
• Cleaned and prepared dataset for training

2. Model Training

• Algorithm: RandomForestClassifier
• Performed train-test split to evaluate model performance

3. Evaluation

• Accuracy
• Precision
• Recall
• F1-score

---

🚀 Results

• Accuracy: ~87% on test set
• The Random Forest model showed strong predictive performance with good accuracy.
• Results demonstrate the usefulness of machine learning for HR decision support.

---

💻 How to Run

1. Clone repository:

git clone https://github.com/your-username/Employee-Attrition-RF.git
cd Employee-Attrition-RF

2. Install dependencies:

pip install -r requirements.txt

3. Run Jupyter Notebook:

jupyter notebook Employee Attrition Prediction.ipynb

---

🔮 Future Work

• Apply GridSearchCV for hyperparameter tuning
• Use SMOTE or other balancing techniques for imbalanced data
• Try other classifiers (Logistic Regression, XGBoost) for comparison
• Build a Streamlit web app for interactive predictions

---

📜 License

MIT License