A Predictive Analytics Framework for Fraud Detection Using Efficient Resampling Based on Hybrid Ensemble Machine Learning

Financial fraud has become a significant threat to companies and organizations in recent years. The extent of bank fraud is difficult to ascertain because much of it remains undisclosed or undetected. Despite numerous measures to prevent financial fraud, it continues to negatively affect individuals and businesses, with losses from fraud on the rise. Today, most financial transactions are conducted virtually worldwide, and online fraud incurs multi-billion-dollar losses for the global economy annually. Consequently, fraud detection has become one among the most formidable real-life problems. Imbalanced datasets are part of the main difficulties in fraud detection. Additionally, the constantly changing nature of fraudulent behavior complicates the instructional process for state-of-the-art binary classifiers in machine learning. In this work, an extensive predictive analytics framework is introduced for identifying fraud cases and addressing the issue of Imbalanced datasets in training fraud detection models. This framework is constructed through the experimentation with a combination of sampling algorithms with Hidden Markov Model, feature engineering techniques. The proposed framework offers a data-centric method utilized for financial credit card analysis of Imbalanced data with real time transactions and is adaptable to other fields in all financial transaction types of large datasets.