🚀 ANN Classification Churn

✨ A deep learning-based classification model to predict customer churn using Artificial Neural Networks (ANN). ✨

📌 Overview

This project leverages an Artificial Neural Network (ANN) to classify customer churn based on historical data. The model is built using TensorFlow and Scikit-Learn and is deployed via Streamlit for easy interaction. 🎯

🔗 GitHub Repository: ANN Classification Churn 🔥
🌐 Live Streamlit App: View Here 🎉

---

📂 Features 🚀

✅ Preprocessed dataset for accurate predictions
✅ Fully connected ANN with optimized hyperparameters
✅ Model evaluation with performance metrics 📊
✅ Interactive UI via Streamlit for real-time classification 🎨
✅ TensorBoard integration for visualization 🖥️

---

⚙️ Installation & Setup 🔧

1️⃣ Clone the repository 💻

git clone https://github.com/laavanjan/ANN-classification-churn.git
cd ANN-classification-churn

2️⃣ Create and activate a Conda environment 🐍

conda create --name ann_env python=3.11 -y
conda activate ann_env

3️⃣ Install dependencies 📦

pip install -r requirements.txt

Alternatively, install manually:

pip install tensorflow==2.15.0 pandas numpy scikit-learn tensorboard matplotlib streamlit ipykernel

---

🚀 Usage 🎯

Running the Model 🏃‍♂️

python app.py  # Modify as needed

Launching Streamlit UI 🌍

streamlit run app.py

Then open http://localhost:8501/ in your browser. 🌐

---

📊 Model Training & Evaluation 🏋️‍♂️

• 📈 The model is trained on labeled customer data.
• 🔄 Uses backpropagation and optimizer tuning for improved accuracy.
• 🎯 Evaluated using precision, recall, and F1-score metrics.
• 🖥️ TensorBoard is used for tracking training performance.

To launch TensorBoard:

tensorboard --logdir=logs

---

📷 Screenshots 🖼️

🤝 Contributing 🤲

💡 Contributions are welcome! Feel free to fork the repo, create a new branch, and submit a pull request. 🚀

---

📝 License 📜

This project is licensed under the GPL License. ⚖️

---

📧 Contact 📩

For any queries, reach out via GitHub Issues or email at your_email@example.com. 📬

---

⭐ Don't forget to star the repo if you find it useful! 🌟