Churn modelling for bank customers using Artificial Neural Network

Churn Modelling

It is very important in the customer retention analysis for any sector. The output of a predictive churn model is a measure of the immediate or future risk of a customer cancellation(in this case whether the customer will stay in the bank or leave the bank) use cases

• to understand why customers are leaving
• to provide incentives to certain customers to prevent them from leaving
• predicting the revenue of the business

Dataset

Kaggle dataset by the name Churn_Modelling.csv

model used

The model used here is a basic Artificial Neural Network(ANN) with 2 hidden layers run for 100 epochs.

Framework and Libraries

-Pandas

-Numpy

-Keras running on Tensorflow backend

-Code compiled and run on Colab

Tip 💡 Easy way to upload local dataset to Colab link

performance metrics