This project predicts customer churn using scikit-learn (LogisticRegression, KNN, RandomForestClassifier) and TensorFlow neural networks. It aims to compare traditional and deep learning models for churn prediction.
- Python 3
- Jupyter Notebook
- Scikit-learn
- Pandas
- NumPy
- Matplotlib
- TensorFlow
- TensorFlow Hub
- Clone the repository.
git clone https://github.com/iamharshvardhan/Customer-Churning-Prediction.git
- Open the
churn-prediction.ipynb
Jupyter Notebook. - Run the cells in the notebook to train and evaluate the deep-learning model.
- We compared sklearn's LogisticRegression, KNearestNeighbour and RandomForestClassifier and tune their hyperparameters to find the most accurate model possible.
- The deep learning model we have used is (
Sequential
) with 3 layers of neural networks.
This project is licensed under the MIT License
.