Financial fraud detection improved with behavior grounded semantic enrichment
Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning
Artificial Intelligence
Summary
Financial fraud detection often struggles because available datasets lack detailed context about transactions, partly due to privacy issues. The authors developed a way to enrich financial data with meaningful descriptions based on actual transaction behavior using specialized agents. This approach creates a new multimodal dataset with both structured and textual information that better reflects real transaction patterns. They show that adding this semantic context helps improve fraud detection and reasoning with large language models.
What this means in practice
- •For financial fraud teams: Improve fraud detection accuracy using enriched transaction data that preserves realistic behavior patterns and provides interpretable semantic context.
- •For large language model developers: Enhance context-aware reasoning on financial data by training models with multimodal datasets that include structured and textual semantic information.
- •For risk management software vendors: Develop anti-fraud products with access to the enriched MS-FFSD dataset that enables realistic fraud modeling combining behavior and semantics.$Commercial implications: Allows building more effective fraud detection tools sold to financial institutions requiring advanced semantic transaction analysis.
Authors
Linbo Shao, Huilin He, Yating Lou, Dawei Cheng
Abstract
In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud reasoning. However, public real-world financial datasets often lack rich semantics due to privacy constraints. Consequently, synthetic datasets incorporate generated semantics, but at the cost of behavioral realism; textual descriptions for contextual reasoning remain scarce. We address this gap through a semantic enrichment framework grounded in original transaction behavior to simulate multimodal financial data. We (1) propose a multi-agent semantic enrichment framework that generates interpretable financial semantics grounded in transaction behavior through role-specialized agents and consistency refinement, and (2) newly contribute a valuable multimodal financial fraud dataset, MS-FFSD, enriched with structured semantics and textual semantics while preserving real-data-grounded transaction behavior. Furthermore, we systematically analyze the quality and utility of semantic enrichment. Results demonstrate statistical fidelity and framework generalizability, while showing that richer semantics benefit fraud modeling and context-aware LLM reasoning. Overall, this work advances multimodal financial fraud research and bridges emerging LLM and multi-agent capabilities with operational anti-fraud practice. The framework and dataset are released at https://github.com/AI4Risk/MS-FFSD.