RetSim

RetSim, a Retail Store Simulator

Since we have access to several years’ worth of transaction data from one of the largest Scandinavian retail shoe store chains, we developed RetSim, a Retail shoe store Simulation, built on the concept of MABS. RetSim is designed to be used in developing and testing fraud scenarios at a retail store, while keeping business sensitive and private personal information about customer’s consumption secret from competitors and others. Simulations in the domain of retail stores have  traditionally been focused on finding answers to logistics problems such as inventory management, supply management, staff scheduling and for customer queue reductions. To our knowledge, RetSim is the first simulator with the purpose of fraud detection on the retail store domain.

The defense against fraud is an important topic that has seen some study. In the retail store the cost of fraud if of course ultimately transferred to the consumer, and finally impacts the overall economy. Our aim with the research leading to RetSim is to learn the relevant parameters that governs the behaviour in and of a retail store to simulate normal behaviour. However, we also model the malicious behaviour and implement detection techniques. As fraud in the retail setting is usually perpetrated by the staff we have focused on that. Examples of such fraud are explained in
sectionretail and includes: Refunds and Coupon Reductions/Discounts.

In terms of the object model used in RetSim the refund fraud scenario was implemented by the following setting: Estimate the average number of refunds per sale and the corresponding standard deviation. Use these statistics for simulating refunds in the RetSim model. Fraudulent salesmen will perform normal refunds, as well as fraudulent ones. The volume of fraudulent refunds can be modelled using a salesman specific parameter. The “red flag” for detection will in this case be a high number of refunds for a salesman. Similar to refund scenario, RetSim generates malicious coupon reduction/discounts and the analysis can also be performed in similar way as with refund fraud.

2016

Lopez-Rojas, Edgar Alonso ; Axelsson, Stefan

A Review of Computer Simulation for Fraud Detection Research in Financial Datasets Inproceedings

Future Technologies Conference, San Francisco, USA, 2016, ISBN: 9781509041718.

Abstract | Links | BibTeX

Lopez-Rojas, Edgar Alonso

Applying Simulation to the Problem of Detecting Financial Fraud PhD Thesis

Blekinge Institute of Technology, 2016, ISBN: 978-91-7295-329-1.

Abstract | Links | BibTeX

2015

Lopez-Rojas, Edgar Alonso

Extending the RetSim Simulator for Estimating the Cost of fraud in the Retail Store Domain Inproceedings

The 27th European Modeling and Simulation Symposium-EMSS, Bergeggi, Italy, 2015, ISBN: 978-88-97999-48-5.

Abstract | Links | BibTeX

Lopez-Rojas, Edgar Alonso ; Axelsson, Stefan

Using the RetSim Fraud Simulation Tool to set Thresholds for Triage of Retail Fraud Inproceedings

20th Nordic Conference on Secure IT Systems, NordSec, pp. 156–171, Springer, Stockholm, 2015, ISBN: 978-3-319-26501-8.

Abstract | Links | BibTeX

Lopez-Rojas, Edgar Alonso ; Gorton, Dan ; Axelsson, Stefan

Using the RetSim simulator for fraud detection research Journal Article

International Journal of Simulation and Process Modelling, 10 (2), pp. 144-155, 2015, ISSN: 1740-2131.

Abstract | Links | BibTeX

2014

Lopez-Rojas, Edgar Alonso

On the Simulation of Financial Transactions for Fraud Detection Research Book

Blekinge Institute of Technology, 2014, ISBN: 978-91-7295-278-2, (Licentiate thesis).

Abstract | Links | BibTeX

Lopez-Rojas, Edgar Alonso ; Axelsson, Stefan

Social Simulation of Commercial and Financial Behaviour for Fraud Detection Research Inproceedings

Advances in Computational Social Science and Social Simulation, Barcelona, 2014, ISBN: 9789172952782.

Abstract | Links | BibTeX

2013

Lopez-Rojas, Edgar Alonso ; Axelsson, Stefan ; Gorton, Dan

RetSim: A Shoe Store Agent-Based Simulation for Fraud Detection Journal Article

The 25th European Modeling and Simulation Symposium, Athens, Greece, 2013, ISBN: 9788897999225, ((Best Paper Award)).

Abstract | Links | BibTeX