Predicting Bank Users’ Time Deposits Based on LSTM-Stacked Modeling

Accurately predicting whether bank users will opt for time deposit products is critical for optimizing marketing strategies and enhancing user engagement, ultimately improving a bank's profitability.Traditional predictive models, such as linear regression and Logistic Regression (LR), are often limited in their ability to capture the complex, time-dependent patterns in user behavior.In this study, a hybrid approach that combines Long Short-Term Memory (LSTM) neural networks and a stacked ensemble learning framework is proposed to address these limitations.Initially, LSTM models were employed to extract temporal features from two distinct bank marketing datasets, thereby capturing the sequential nature of user interactions.These extracted features were subsequently input into several base classifiers, including Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbour (KNN), to conduct initial classifications.The outputs of these classifiers were then integrated using a LR model for final decision-making through a stacking ensemble method.The experimental evaluation demonstrates that the proposed LSTM-stacked model outperforms traditional models in predicting user time deposits on both datasets, providing robust predictive performance.The results suggest that leveraging temporal feature extraction with LSTM and combining it with ensemble techniques yields superior prediction accuracy, thereby offering a more sophisticated solution for banks aiming to enhance their marketing efficiency.