Predicting Customer Term Deposit Subscriptions with Machine Learning
Understanding customer behavior is key for successful marketing in the banking sector. This project uses Machine Learning techniques to analyze direct marketing campaign data and predict whether a customer will subscribe to a term deposit. Factors such as age, occupation, marital status, and past interactions help uncover valuable insights.
We use classification models like Logistic Regression, Random Forest, and XGBoost to build an accurate prediction system.
The dataset is preprocessed and analyzed using EDA and feature engineering.
Model performance is validated using metrics such as accuracy, precision, recall, F1-score, and ROC-AUC, providing actionable intelligence to optimize marketing strategies.