Research on Advance Machine Learning Based Decision Support System for Frauds Detection and Prevention in Online Banking System

Abstract

The rise in online banking fraud, driven by the underground malware economy, underscores the crucial need for robust fraud analysis systems. Regrettably, the majority of existing approaches rely on black box models that lack transparency and fail to provide justifications to analysts. Additionally, the scarcity of available Internet banking data for the scientific community hinders the development of effective methods. This paper presents a decision support system meticulously crafted to identify and thwart fraud in online banking transactions. The chosen approach involves the application of a Random Forest decision tree model—a supervised machine learning technique renowned for its effectiveness in enhancing fraud detection within online banking systems, yielding substantial real-world impact. Constant monitoring of both the system and data ensures optimal performance, enabling timely responses to deviations. The overarching objective of the system is to furnish analysts with a powerful decision support tool capable of preempting financial crimes before they occur.