Code Word Detection in Fraud Investigations using a Deep-Learning Approach

TL;DR

This paper presents a deep learning approach using BERT to detect code words in email communications, aiding fraud investigations by automating the identification of deceptive language.

Contribution

It introduces a novel synthetic dataset and demonstrates that BERT significantly outperforms other methods in detecting code words in fraud-related texts.

Findings

BERT achieves an F1 score of 0.9 in code word detection.

Deep neural language models are effective for fraud investigation tasks.

The framework helps organize data for easier investigative analysis.

Abstract

In modern litigation, fraud investigators often face an overwhelming number of documents that must be reviewed throughout a matter. In the majority of legal cases, fraud investigators do not know beforehand, exactly what they are looking for, nor where to find it. In addition, fraudsters may use deception to hide their behaviour and intentions by using code words. Effectively, this means fraud investigators are looking for a needle in the haystack without knowing what the needle looks like. As part of a larger research program, we use a framework to expedite the investigation process applying text-mining and machine learning techniques. We structure this framework using three well-known methods in fraud investigations: (i) the fraud triangle (ii) the golden ("W") investigation questions, and (iii) the analysis of competing hypotheses. With this framework, it is possible to automatically organize investigative data, so it is easier for investigators to find answers to typical investigative questions. In this research, we focus on one of the components of this framework: the identification of the usage of code words by fraudsters. Here for, a novel (annotated) synthetic data set is created containing such code words, hidden in normal email communication. Subsequently, a range of machine learning techniques are employed to detect such code words. We show that the state-of-the-art BERT model significantly outperforms other methods on this task. With this result, we demonstrate that deep neural language models can reliably (F1 score of 0.9) be applied in fraud investigations for the detection of code words.