Using Machine Learning to Detect Financial Statement Fraud: A Cross-Country Analysis Applied to Wirecard AG
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".