Using the RetSim simulator for fraud detection research

Managing fraud is important for business, retail and financial alike. One method to manage fraud is by detection, where transactions, etc. are monitored and suspicious behaviour is flagged for further investigation. There is currently a lack of public research in this area. The main reason is the sensitive nature of the data. Publishing real financial transaction data would seriously compromise the privacy of both customers, and companies alike. We propose to address this problem by building RetSim, a multi-agent-based simulation (MABS) calibrated with real transaction data from one of the largest shoe retailers in Scandinavia. RetSim allows us to generate synthetic transactional data that can be publicly shared and studied without leaking business sensitive information, and still preserve the important characteristics of the data. We then use RetSim to model two common retail fraud scenarios to ascertain exactly how effective the simplest form of statistical threshold detection could be. The preliminary results of our tested fraud detection method show that the threshold detection is effective enough at keeping fraud losses at a set level, that there is little economic room for improved techniques.