Churn-Prediction-JOB-A-THON---March-2022-

Data Description

ID = Unique Identifier of a row Age = Age of the customer Gender = Gender of the customer (Male and Female) Income = Yearly income of the customer Balance = Average quarterly balance of the customer Vintage = No. of years the customer is associated with bank Transaction_Status = Whether the customer has done any transaction in the past 3 months or not Product_Holdings = No. of product holdings with the bank Credit_Card = Whether the customer has a credit card or not Credit_Category = Category of a customer based on the credit score Is_Churn = Whether the customer will churn in next 6 months or not

Problem

Analyze the data of a customer and predict whether the customer will churn or not in the future.

Models Used

Ensemble model - LGBM, Xgboost and CatBoost