Customer Churn Prediction using Artificial Neural Networks (ANN)
Overview
This project builds a deep learning model using an Artificial Neural Network (ANN) to predict customer churn. It is implemented in Python using Jupyter Notebook and leverages deep learning frameworks like TensorFlow/Keras.
Features
-
Data preprocessing and feature engineering
-
ANN model architecture with input, hidden, and output layer
-
Model training and evaluation using accuracy and loss metrics
-
Predictions and insights for business decision-making
Installation
1. Clone the repository:
git clone https://github.com/your-username/Customer-Churn-Prediction-ANN.git
2. Install dependencies:
pip install -r requirements.txt
3. Usage
Run the Jupyter Notebook to execute the steps for data processing, model training, and prediction:
jupyter notebook Customer_Churn_Prediction_ANN.ipynb
Results
-
Performance metrics such as accuracy, precision, recall, and F1-score
-
Visualization of training loss and accuracy
-
Business insights on customer churn behavior
Contributing
Feel free to submit pull requests or open issues for improvements.
License
This project is open-source under the MIT License.