Churn Prediction - Ride Sharing Services

Predicted possibility of customer churning, understand what factors are the best predictors for retention, and offer suggestions to operationalize those insights to help Company X.

Files in src and how to use

• main.py: prepare data for modeling
• decision_tree.py: decision tree model
• logistic_regression_eda: data exploration, cross validation and model tuning of logistic regression model
• tree_models_knn.py: Random forest, Adaboost, Gradient Boosting and kNN model building, feature importance exploration and grid search

Rough timeline

• First 3 hours: EDA, Feature Engineering
• Next 3 hours: Model building and deployment

Credits

This project would not be possible without the efforts of my fellow teammates Elham Ke, Jianda Zhou and Nikhil Makaram.