Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/priyanshu1303d/churn-prediction
The model analyzes various customer attributes to predict whether a customer is likely to leave the bank.
https://github.com/priyanshu1303d/churn-prediction
artificial-neural-networks deep-learning keras tensorflow
Last synced: 8 days ago
JSON representation
The model analyzes various customer attributes to predict whether a customer is likely to leave the bank.
- Host: GitHub
- URL: https://github.com/priyanshu1303d/churn-prediction
- Owner: Priyanshu1303d
- Created: 2024-11-16T06:37:50.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2024-11-17T04:31:52.000Z (2 months ago)
- Last Synced: 2025-01-21T09:11:54.849Z (8 days ago)
- Topics: artificial-neural-networks, deep-learning, keras, tensorflow
- Language: Jupyter Notebook
- Homepage: https://churn-prediction-mkc6xwmyt27rlps7noqebq.streamlit.app/
- Size: 378 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Customer Churn Prediction using Artificial Neural Networks 🎯
This project implements a machine learning solution to predict customer churn in a banking context using Artificial Neural Networks (ANN). The model analyzes various customer attributes to predict whether a customer is likely to leave the bank.
## 🔴 Live Demo
Check out the live application: [Bank Customer Churn Predictor](https://churn-prediction-mkc6xwmyt27rlps7noqebq.streamlit.app/)
## 📊 Project Overview
The system predicts customer churn based on features including:
- Credit Score
- Gender
- Age
- Tenure
- Balance
- Number of Products
- Credit Card Status
- Activity Status
- Estimated Salary
- Geography (France, Germany, Spain)
## 🗂️ Project Structure
```
├── data/ # Data files directory
├── logs/ # Training logs
├── venv/ # Python virtual environment
├── app.py # Streamlit application file
├── experiments.ipynb # Experimentation notebook
├── prediction.ipynb # Prediction examples
├── model.h5 # Trained neural network model
├── sc.pkl # Standard scaler object
├── ohe_geo.pkl # One-hot encoder for geography
├── label_encoder_gender.pkl # Label encoder for gender
└── requirements.txt # Project dependencies
```
## 🚀 Getting Started
### Prerequisites
- Python 3.12
- pip package manager
### Installation
1. Clone the repository:
```bash
git clone https://github.com/Priyanshu1303d/churn-prediction.git
cd churn-prediction
```
2. Create and activate virtual environment:
```bash
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
3. Install required packages:
```bash
pip install -r requirements.txt
```
## 💻 Usage
### Running Locally with Streamlit
Run the Streamlit application:
```bash
streamlit run app.py
```
The application will open in your default web browser.
### Deploying to Streamlit Cloud
1. Push your code to GitHub
2. Visit [Streamlit Cloud](https://streamlit.io/cloud)
3. Create a new app and connect it to your GitHub repository
4. Select app.py as the main file
5. Deploy!
## 🔄 Model Pipeline
1. **Data Preprocessing**:
- Gender encoding using LabelEncoder
- Geography encoding using OneHotEncoder
- Feature scaling using StandardScaler
2. **Model Architecture**:
- Input Layer: Features dimension
- Hidden Layers: Dense layers with ReLU activation
- Output Layer: Single neuron with sigmoid activation
## 📦 Dependencies
Main dependencies include:
- TensorFlow
- Keras
- scikit-learn
- pandas
- numpy
- streamlit
See `requirements.txt` for complete list.
## 🛠️ Development
To experiment with the model:
1. Open `experiments.ipynb` for model training and evaluation
2. Use `prediction.ipynb` for testing predictions
3. Modify `app.py` for Streamlit interface changes
## 📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
## 📧 Contact
Project Link: [https://github.com/Priyanshu1303d/churn-prediction](https://github.com/Priyanshu1303d/churn-prediction)
Built by Priyanshu