MétaCan
Menu
Back to cohort
Record W4415649477 · doi:10.3390/jrfm18110605

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

2025· article· en· W4415649477 on OpenAlexvenueno aff
Luca Steingen, Edgar Löw

Bibliographic record

VenueJournal of risk and financial management · 2025
Typearticle
Languageen
FieldComputer Science
TopicImbalanced Data Classification Techniques
Canadian institutionsnot available
Fundersnot available
KeywordsFinancial statementVendorPipeline (software)Boosting (machine learning)Gradient boostingStatement (logic)Ensemble learning

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.920
Threshold uncertainty score0.683

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.010
GPT teacher head0.284
Teacher spread0.274 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreMethods

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".

Quick stats

Citations2
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of risk and financial managementSame topicImbalanced Data Classification TechniquesFrench-language works237,207