CREDIT CARD FRAUD DETECTION USING A STACKING ENSEMBLE APPROACH WITH LSTM AND RANDOM FOREST MACHINE LEARNING TECHNIQUES

Credit cards play an essential role in today's digital economy, and their usage has recently grown tremendously, accompanied by a corresponding increase in credit card fraud. Machine learning (ML) algorithms have been utilized for credit card fraud detection. However, the dynamic shopping patterns of credit card holders and the class imbalance problem have made it difficult for ML classifiers to achieve optimal performance. This research project aims to develop a reliable credit card fraud detection system through a stacking ensemble method, integrating LSTM and Random Forest machine learning techniques. This approach aims to enhance fraud detection accuracy by leveraging the diverse strengths of both models. The system will undergo rigorous evaluation to ensure its efficiency in identifying fraudulent transactions while minimizing false positives. By combining the temporal sequencing capabilities of LSTM with the decision-making process of Random Forest, the proposed approach seeks to achieve heightened sensitivity to fraudulent patterns while maintaining computational efficiency. Ultimately, the objective is to bolster security measures and protect financial institutions and consumers from potential fraud risks.