GitHub - nikhil97353/Churn-Prediction: This project focuses on predicting customer churn, the goal is to identify customers at risk of leaving and develop machine learning models to predict churn. Various classifiers like Random Forest, XGBoost, and Neural Networks are used, with metrics such as accuracy, precision, recall, and F1-score to evaluate model performance.

nikhil97353 / Churn-Prediction Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

This project focuses on predicting customer churn, the goal is to identify customers at risk of leaving and develop machine learning models to predict churn. Various classifiers like Random Forest, XGBoost, and Neural Networks are used, with metrics such as accuracy, precision, recall, and F1-score to evaluate model performance.

MIT license

0 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
Churn_Prediction.ipynb		Churn_Prediction.ipynb
Churn_Prediction.py		Churn_Prediction.py
Churn_ROC.png		Churn_ROC.png
Churn_recall.png		Churn_recall.png
LICENSE		LICENSE
Readme		Readme
requirements.txt		requirements.txt

Repository files navigation

This project aims to predict customer churn using several machine learning classifiers and compare their performance. The dataset used contains customer-related features such as account balance, credit score, and demographic details. Seven machine learning classifiers are implemented to identify whether a customer will leave (churn) or stay.

Machine Learning Models:
Logistic Regression
K-Nearest Neighbors
Support Vector Machine
Decision Tree
Random Forest
XGBoost
Neural Network (MLPClassifier)
Model Evaluation: Evaluated performance using:
Accuracy
Precision
Recall
F1-Score
ROC AUC Score
Confusion Matrix
Visualization: Generated visualizations for each model, including ROC and Precision-Recall curves.

Performance Metrics:
Logistic Regression: Accuracy: 81%; K-Nearest Neighbors: Accuracy: 83%; Random Forest: Accuracy: 86%; XGBoost: Accuracy: 86%; Neural Network: Accuracy: 85%