Bank Customer Churn Prediction Using Neural Networks
Mar 2020 - Apr 2020 (2 months)
This project involves building a neural network classifier to predict whether a bank customer will leave the bank within the next six months, based on an open-source dataset from Kaggle. The dataset contains 10,000 records with 14 features, including customer demographics, account information, and credit details. The project focuses on pre-processing the data by removing unique identifiers, normalizing features, and dividing the data into training and testing sets. Using Python and deep learning techniques, a neural network model is built, evaluated, and improved to achieve higher accuracy in predicting customer churn. This project highlights skills in data preparation, model building, and performance evaluation using confusion matrices and