Catch me if you can: In search of accuracy, scope, and ease of fraud prediction. (Chakrabarty et al., 2024)

Welcome to Revise and Resubmit, the podcast where we break down academic research to uncover the stories, insights, and innovations that shape our understanding of the world. Today, we’re diving deep into a topic that’s as thrilling as it is critical—fraud prediction. Think of it as a game of cat and mouse, but with billions of dollars at stake. The episode is centered around a recent publication in the FT50 Journal Review of Accounting Studies titled 'Catch Me if You Can: In Search of Accuracy, Scope, and Ease of Fraud Prediction.' This paper, published on September 21, 2024, introduces two revolutionary fraud prediction metrics—the AB-score and the ABF-score. Both metrics promise more accuracy, expanded scope, and simpler estimation methods compared to traditional models. In the business world, fraud can strike at any time, leaving companies and investors reeling. Imagine the stakes: $14.34 billion saved annually by simply predicting fraud more effectively. It sounds like a magic bullet, but is it? Can fraud really be predicted, and if so, what does that mean for the future of financial transparency? We'll break down how these models work, why they matter, and what the implications are for businesses and stakeholders. So, what makes fraud so elusive, and can these new models finally catch it in its tracks? Or will fraud always find a way to stay one step ahead? Let’s find out. Reference Chakrabarty, B., Moulton, P.C., Pugachev, L. et al. Catch me if you can: In search of accuracy, scope, and ease of fraud prediction. Rev Account Stud (2024). https://doi.org/10.1007/s11142-024-09854-4