Our paper "Towards Explainable Occupational Fraud Detection" has been accepted at MIDAS 202222.07.2022
In our paper, we investigate the performance and interpretability of machine learning approaches when detecting occupational fraud in company data, finding models that give both strong performance and comprehensible decisions.
Our paper investigates the performance and interpretability of current machine learning models on data from enterprise resource planning systems. We will present our work as part of the 7th Workshop on MIning DAta for financial applicationS (MIDAS) which takes place as part of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) on 23.09.2022.
Occupational fraud within companies currently causes losses of around 5% of company revenue each year. While enterprise resource planning systems can enable automated detection of occupational fraud through recording large amounts of company data, the use of state-of-the-art machine learning approaches in this domain is limited by their untraceable decision process. In this study, we evaluate whether machine learning combined with explainable artificial intelligence can provide both strong performance and decision traceability in occupational fraud detection. We construct an evaluation setting that assesses the comprehensibility of machine learning-based occupational fraud detection approaches, and evaluate both performance and comprehensibility of multiple approaches with explainable artificial intelligence. Our study finds that high detection performance does not necessarily indicate good explanation quality, but specific approaches provide both satisfactory performance and decision traceability, underlining the suitability of machine learning for practical application in occupational fraud detection and the importance of research evaluating both performance and comprehensibility together.