Using Machine Learning to Detect Financial Statement Fraud: A Cross-Country Analysis Applied to Wirecard AG

This study analyzes the ability of machine-learning algorithms to detect financial statement fraud using four financial ratios as inputs: the Altman Z-Score, Beneish M-Score, Montier C-Score, and Dechow F-Score. It also evaluates whether the Wirecard AG scandal of 2020 could have been detected by the model developed in this study. Financial statement data was obtained from the financial data vendor Bloomberg L.P. The dataset consists of 2,014,827 firm years between 1988–2019, from companies across the globe, of which 1145 firm years were identified as fraudulent. A balanced dataset of 1046 fraudulent firm years and 1046 randomly selected firm years was used to train and evaluate multiple machine-learning algorithms via an automated pipeline search. The selected model is an ensemble combining gradient boosting and k-nearest neighbors. On the held-out test set, it correctly classified 82.03% of the manipulated and 89.88% of the non-manipulated firm years, with an overall accuracy of 85.69%. Applied retrospectively to Wirecard AG, the model identified 7 of 17 firm years as fraudulent.