A Domain-Specific Transformer Approach for Financial Statement Fraud Detection
Bibliographic record
Abstract
Financial statement fraud poses significant risks to investors, regulators, and businesses. To address this issue, various detection techniques have been developed. This paper introduces a novel approach utilizing a transformer neural network model, specifically leveraging the Bidirectional Encoder Representations from Transformers (BERT), to detect financial statement fraud through the textual data in the management's discussion and analysis (MD&A) sections. The textual data are transformed into numerical vectors using BERT embeddings. We evaluate our approach on a dataset comprising fraudulent and non-fraudulent U.S. financial statements. The results demonstrate that the transformer model with FinBERT embeddings achieves the highest accuracy of 0.83, with a fraud precision of 0.82, and a fraud recall of 0.79. Additionally, comparisons with traditional RNN, LSTM, and GRU models show the transformer's superior performance. These findings underscore the powerful predictive capabilities of the transformer model, particularly in accurately identifying non-fraudulent financial statements.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| 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".