Churn prediction aims to detect customers intended to leave a service provider.Here the prediction is done on bank customers.This modelling enables the companies or organisations to identify the areas where they lag behind, thereby enabling them to rectify those issues and also aid in increasing the retention rate. The machine learning technique used in this project is Artificial Neural Network without momentum.
The considered data set contains details of a bank's customers and the target variable is a binary variable reflecting the fact whether the customer leave the bank (closed his account) or he continues to be a customer. Dataset can be found in the repository or download the dataset from https://www.kaggle.com/shrutimechlearn/churnmodelling?select=Churn_Modelling.csv
Model that is built gives the training accuracy of 87% and a testing accuracy of 85%.