This project predicts customer churn in the banking sector using Artificial Neural Networks (ANN). It analyzes customer data to identify patterns of potential churn, enabling proactive retention strategies. The model’s performance is evaluated using accuracy, precision, recall, and F1-score.
Data Preprocessing: Includes handling missing values, encoding categorical variables, and feature scaling. Model Building: Artificial Neural Network (ANN) constructed using TensorFlow/Keras for churn prediction. Evaluation: Performance of the model is evaluated using accuracy, precision, recall, F1-score, and ROC-AUC.
Python TensorFlow / Keras Scikit-learn Pandas Matplotlib/Seaborn (for visualization)
This repository serves as a practical demonstration of using ANN for churn prediction and can be extended or modified for other predictive analytics tasks.