artificial-neural-network-business_case_study and Customer-Churn-Prediction-using-Artificial-Neural-Network
About artificial-neural-network-business_case_study
TatevKaren/artificial-neural-network-business_case_study
Business Case Study to predict customer churn rate based on Artificial Neural Network (ANN), with TensorFlow and Keras in Python. This is a customer churn analysis that contains training, testing, and evaluation of an ANN model. (Includes: Case Study Paper, Code)
This project helps banks and financial institutions predict which customers are likely to leave, enabling proactive retention strategies. By analyzing customer characteristics (e.g., account history, demographics), it provides a probability score for each customer indicating their likelihood of churning. This helps risk analysts, marketing managers, and customer relationship managers identify and focus on at-risk customers.
About Customer-Churn-Prediction-using-Artificial-Neural-Network
vishal815/Customer-Churn-Prediction-using-Artificial-Neural-Network
This project involves building an Artificial Neural Network (ANN) for predicting customer churn. The dataset used contains various customer attributes, and the ANN is trained to predict whether a customer is likely to leave the bank.
Implements a sequential neural network with two hidden layers using TensorFlow/Keras, incorporating standard preprocessing pipelines (label encoding, one-hot encoding, feature scaling) and binary crossentropy optimization. The model achieves 86.3% accuracy through 100 epochs of training on the Churn_Modelling dataset. Includes prediction examples with detailed formatting requirements for categorical variable encoding.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work