- This project is a customer churn prediction system built using the Telco Customer Churn dataset.
- The dataset contains information about customer demographics, payment details and services that the customer signed up for.
- Trained and evaluated various machine learning models such as Logistic Regression, SVC, Random Forest Classifier, Decision Tree Classifier, XGBoost Classifier, LightGBM Classifier.
- Performed feature selection using Recursive Feature Elimination technique and tuned the hyperparameters for the best performing model, the Logistic Regression model.
- Logistic Regression model predicts whether the customer is likely to churn or happy with the services, with an accuracy score of 81.1% and an F1 score of 80.6%.
- Saved the best model using joblib library and used it to build an interactive web application.
- Built the web app using Streamlit and deployed it on Heroku.
- You can take a look at the interactive demo to see how the customer churn prediction system works.
- You can get online predictions by filling out the form in the web application.
- You can use this sample dataset to experiment with the batch prediction.