Customer Churn Prediction

Dataset

The dataset used is Churn_Modelling.csv, which includes features related to customer demographics, financial behavior, and service engagement.

Features

CreditScore: Customer's credit score.

Geography: Customer's geographic location.

Gender: Customer's gender.

Age: Customer's age.

Tenure: Number of years the customer has been with the company.

Balance: Customer's account balance.

NumOfProducts: Number of products the customer uses.

HasCrCard: Whether the customer has a credit card (1 = Yes, 0 = No).

IsActiveMember: Whether the customer is an active member (1 = Yes, 0 = No).

EstimatedSalary: Customer's estimated annual salary.

Exited: Target variable indicating if the customer has exited (1 = Yes, 0 = No).

Results

KNN: Accuracy - 83%, ROC-AUC - 0.90

Naive Bayes: Accuracy - 76%, ROC-AUC - 0.84

SVM: Accuracy - 88%, ROC-AUC - 0.95

Decision Tree: Accuracy - 82%, ROC-AUC - 0.82

Conclusion

The SVM model performed the best, with the highest accuracy and ROC-AUC score. Further improvements can be made through hyperparameter tuning and feature engineering.