%0 Journal Article %1 tritscher2024generation %A Tritscher, Julian %A Wolf, Maximilian %A Krause, Anna %A Hotho, Andreas %A Schlör, Daniel %D 2024 %J 47th German Conference on Artificial Intelligence (KI 2024) - to appear %K anomaly_detection author:hotho author:krause author:schloer author:tritscher author:wolf csf fraud_detection from:tritsch myown research_xai xai %T Data Generation for Explainable Occupational Fraud Detection %X Occupational fraud, the deliberate misuse of company assets by employees, causes damages of around 5% of yearly company revenue. Recent work therefore focuses on automatically detecting occupational fraud through machine learning on the company data contained within enterprise resource planning systems. Since interpretability of these machine learning approaches is considered a relevant aspect of occupational fraud detection, first works have already integrated post-hoc explainable artificial intelligence approaches into their fraud detectors. While these explainers show promising first results, systematic advancement of explainable fraud detection methods is currently hindered by the general lack of ground truth explanations to evaluate explanation quality and choose suitable explainers. To avoid expensive expert annotations, we propose a data generation scheme based on multi-agent systems to obtain company data with labeled occupational fraud cases and ground truth explanations. Using this data generator, we design a framework that enables the optimization of post-hoc explainers for unlabeled company data. On two datasets, we experimentally show that our framework is able to successfully differentiate between explainers of high and low explanation quality, showcasing the potential of multi-agent-simulations to ensure proper performance of post-hoc explainers.

@article{tritscher2024generation, abstract = {Occupational fraud, the deliberate misuse of company assets by employees, causes damages of around 5% of yearly company revenue. Recent work therefore focuses on automatically detecting occupational fraud through machine learning on the company data contained within enterprise resource planning systems. Since interpretability of these machine learning approaches is considered a relevant aspect of occupational fraud detection, first works have already integrated post-hoc explainable artificial intelligence approaches into their fraud detectors. While these explainers show promising first results, systematic advancement of explainable fraud detection methods is currently hindered by the general lack of ground truth explanations to evaluate explanation quality and choose suitable explainers. To avoid expensive expert annotations, we propose a data generation scheme based on multi-agent systems to obtain company data with labeled occupational fraud cases and ground truth explanations. Using this data generator, we design a framework that enables the optimization of post-hoc explainers for unlabeled company data. On two datasets, we experimentally show that our framework is able to successfully differentiate between explainers of high and low explanation quality, showcasing the potential of multi-agent-simulations to ensure proper performance of post-hoc explainers.}, added-at = {2024-07-08T17:04:17.000+0200}, author = {Tritscher, Julian and Wolf, Maximilian and Krause, Anna and Hotho, Andreas and Schlör, Daniel}, biburl = {https://www.bibsonomy.org/bibtex/28cff9d35fb1279d1129f0ee7fc7f061d/dmir}, description = {Accepted and to appear at the 47th German Conference on Artificial Intelligence - KI 2024}, interhash = {51d383d3f537216387bd18df456fbed5}, intrahash = {8cff9d35fb1279d1129f0ee7fc7f061d}, journal = {47th German Conference on Artificial Intelligence (KI 2024) - to appear}, keywords = {anomaly_detection author:hotho author:krause author:schloer author:tritscher author:wolf csf fraud_detection from:tritsch myown research_xai xai}, timestamp = {2024-07-08T17:08:28.000+0200}, title = {Data Generation for Explainable Occupational Fraud Detection}, year = 2024 }