March 3, 2026Open Access

A Domain-Specific Transformer Approach for Financial Statement Fraud Detection

Key Points

Accuracy achieved is 0.83, demonstrating the effectiveness of BERT embeddings for fraud detection.
Fraud precision is reported at 0.82, while fraud recall stands at 0.79, showcasing model reliability.
Assessment of transformer model compared to traditional RNN, LSTM, and GRU highlights superior performance.
Findings emphasize the predictive power of transformer models in distinguishing fraudulent financial statements.

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.

Demander à l'IA

Bookmark

View Full Paper