README.md

🎓 Final Year Project — Customer Churn Prediction

Predicting customer churn using supervised machine learning techniques — achieving high accuracy through EDA, feature engineering, and ensemble methods.

---

📌 Overview

This project applies machine learning to solve a real-world business problem: predicting customer churn. By identifying customers likely to leave, businesses can take proactive retention actions, saving revenue and improving customer satisfaction.

Key Achievements:

• Built and compared multiple ML models (Logistic Regression, Random Forest, XGBoost)
• Performed full EDA with detailed visualizations
• Achieved strong prediction accuracy through hyperparameter tuning
• Deployed clean, well-documented Jupyter notebooks

---

🗂️ Project Structure

Final-Year-Project/
├── 📓 Zahoor_coding_Pa...ipynb    # Main analysis notebook
├── 📄 churn-prediction-r...ipynb  # Churn prediction model
└── 📋 README.md

---

🔬 Methodology

Step	Description
1. Data Collection	Sourced real-world customer dataset
2. EDA	Exploratory Data Analysis with visualizations
3. Preprocessing	Handling nulls, encoding, feature scaling
4. Modelling	Logistic Regression, Random Forest, XGBoost
5. Evaluation	Accuracy, Precision, Recall, F1, ROC-AUC
6. Insights	Business recommendations from findings

---

🛠️ Tech Stack

Category	Tools
Language	Python 3.9+
Data	Pandas, NumPy
Visualisation	Matplotlib, Seaborn
ML	Scikit-Learn, XGBoost
Environment	Jupyter Notebook

---

🚀 Getting Started

# Clone the repo
git clone https://github.com/hacker007S/Final-Year-Project.git
cd Final-Year-Project

# Install dependencies
pip install pandas numpy scikit-learn matplotlib seaborn xgboost jupyter

# Launch Jupyter
jupyter notebook

---

👤 Author

Zahoor Khan — CEO @ PyCode Ltd

---

_{⭐ Star this repo if you found it useful!}