Churn-Modelling-Artificial-Neural-Network

About

This data set contains details of a bank's customers and the target variable is a binary variable reflecting the fact whether the customer left the bank (closed his account) or he continues to be a customer.We have to build the model whether the customer left the bank (closed his account) or he continues to be a customer.

Model

Artificial Neural Networks (ANN) are multi-layer fully-connected neural nets that look like the figure below. They consist of an input layer, multiple hidden layers, and an output layer. Every node in one layer is connected to every other node in the next layer. We make the network deeper by increasing the number of hidden layers.

Models with their Accuracy of Prediction

• Accuracy of the model is 86%
• I have done the Hyperparameter tuning and finally reached the accuracy of 91%

Dependencies

 Keras
 Tensorflow V2.6.0
 Pandas
 Scikit-Learn
 Numpy
 python 3.9
 

Usage

Just run jupyter notebook in terminal and it will run in your browser.

Install Jupyter here i've you haven't.

Links for Python Notebooks used for model creation

• https://github.com/rahkum96/Churn-Modelling-Artificial-Neural-Network/blob/main/Churn_Modelling_ANN_model.ipynb
• https://github.com/rahkum96/Churn-Modelling-Artificial-Neural-Network/blob/main/Churn_Modelling_ANN_Hyperparameter.ipynb

Steps to run this notebook in your system:

• Clone or download the repo.
• Open command prompt in the downloaded folder.

Dataset link:

https://www.kaggle.com/shrutimechlearn/churn-modelling