ABSTRACT
Fraud is as old as humankind and appears in many types and forms. Popular examples are credit card fraud, tax evasion, identity theft, insurance fraud, counterfeit, click fraud, anti-money laundering, and payment transaction fraud. In earlier research we defined fraud as an uncommon, well-considered, imperceptibly concealed, time-evolving, and carefully organized crime. Nowadays, fraud is typically tackled using state-of-the-art analytical techniques with many accompanying challenges. It is the purpose of this article to highlight twelve research topics (RTs) that we believe prioritize high on the agenda of contemporary fraud analytics models. We do this by reviewing fraud analytics from a data, model, performance, and deployment perspective.
Disclosure statement
No potential conflict of interest was reported by the author.
Additional information
Notes on contributors
B. Baesens
B. Baesens is a professor of Big Data & Analytics at KU Leuven (Belgium), and a lecturer at the University of Southampton (United Kingdom). He has done extensive research on big data & analytics, credit risk modeling, fraud detection, and marketing analytics. He co-authored more than 250 scientific papers and 10 books. Bart received the OR Society’s Goodeve medal for best JORS paper in 2016 and the EURO 2014 and EURO 2017 award for best EJOR paper. His research is summarized at www.dataminingapps.com. Bart is listed in the top 2% of Stanford University’s new Database of Top Scientists in the World. He also has his own ON-LINE learning BlueCourses platform: www.bluecourses.com which features courses on machine learning, credit risk, fraud, marketing, text analytics, deep learning, web scraping etc.