With the rapid proliferation in the sophistication and volume of financial crime, financial institutions need to prevent crime on the front lines against the financial threat. The advancements in Information Technology (IT) enhance how people activity with organizations in terms of exchanging financial information and executing transactions. Consequently, the opportunity of launching malware has increased to extract financial information. Hence, detecting financial crime is one of the important prevention and investigation research areas in the field of malware forensics.
Financial cybercrime is the crime launched over cyberspace to steal money by internet criminals. Identifying the perpetrators in the financial cybercrime is difficult due to the masking activities of the criminals as the normal activity of the customer behavior or financial service. Anomaly detection models have gained significant attention in identifying the irregular behavioral patterns in the banking and finance sectors.
In recent years, financial cybercrime detection and prediction systems have increasingly adopted feature engineering, anomaly detection, and deep learning techniques. To protect the assets of the customers and identify malicious behavior, developing intelligent financial crime prediction is imperative over the highly dynamic and diversified user behavioral patterns.