Churn-Prediction-Classification-Datascience-Project

This is a Machine Learning project that predicts whether a customer will stop using the product or service(churn) based on their historical data provided by the Bank.

Problem Statement:

Here the prediction is about Whether the customer will continue using the product or service or stops using it. This project aims to predict the churn based on various factors such as Credit Score, Geographical Location, Gender, Age, Tenure of the product usage, Balance pending,Number of products, Has Credit card or Not, Active Member or not and Estimated Salary given.

Solution Approach:

The project uses a machine learning model which gives the highest accuracy rate to predict the churn of the customer. The model is trained using the dataset provided by the bank and it uses the features in the dataset to predict the Churn with highest accurate rate.

Observations:

The project found that the following factors are most important in predicting the Stoppage of usage(Churn)

• Credit Score
• Geographical Location
• Gender
• Age
• Tenure of the usage
• Balance pending
• Number of products
• Credit Card Availability
• Activity of usage
• Estimated salary

Insights:

The project provides insights into the factors that influence the exiting of the customer(churn). This information can be used by bank to predict whether the customer continue with their services and products or not. This can be used to the advantage of the bank and help their business hit high.

Findings:

The project found that the machine learning model was able to predict the churn of the customer with high degree of accuracy. The model was able to predict the churn of the customer with more than 95% accuracy rate. The project also found that the model was able to generalize well to new data. The model was able to predict the churn of the customer with the appropriate input data.