Data Science Chair

    We provide public ERP system data for automated fraud detection


    We've created an approach for constructing synthetic ERP system data with different cases of occupational fraud to help researchers develop automated detection approaches.

    Occupational fraud, where employees abuse their organization's assets, are losing companies around 5% of their revenue each year.

    In our research project DeepScan, we develop approaches to automatically detect this type of fraud in data recorded by Enterprise Ressource Planning (ERP) systems, that track large amounts of information of company operation. Achieving openly reproducible progress on this task is difficult, since real ERP system data is guarded by companies to not reveal trade secrects or information regarding their employees.

    To advance research in this area, we proposed a data generation strategy that is able to create synthetic normal and fraudulent ERP system data free of privacy and trade secret concerns through an existing serious game, ERPsim. We provide data generated through our approach on our website to aid researchers, and describe our data generation approach in depth in the corresponding paper.