Author(s)

Laura Chen, Robert Murphy*

Affiliation(s)

University of Notre Dame, Notre Dame, USA.

Corresponding Author

Robert Murphy

ABSTRACT

The increasing complexity of financial transaction networks has necessitated the development of sophisticated analytical tools capable of uncovering intricate relationships within heterogeneous financial data while maintaining interpretability for regulatory compliance and fraud detection purposes. This paper presents a novel framework for interpretable transformer models specifically designed for relationship analysis in financial transaction networks. Our approach builds upon the foundational attention mechanisms developed for sequence-to-sequence tasks and extends them through graph attention networks to handle complex multi-entity financial relationships. The framework demonstrates how attention-based architectures can effectively analyze heterogeneous networks comprising card numbers, transaction identifiers, email domains, and card types to identify suspicious patterns and fraudulent activities. We develop specialized visualization techniques that reveal temporal dependencies in transaction sequences and cross-entity correlations in financial networks. Experimental evaluation on real-world financial transaction datasets demonstrates that our interpretable transformer models achieve superior performance in fraud detection while providing actionable insights for financial analysts. The framework successfully identifies complex fraud patterns including coordinated attacks across multiple entity types, suspicious email-card associations, and abnormal transaction behaviors, with interpretability metrics showing high alignment with expert fraud analyst assessments.

KEYWORDS

Interpretable machine learning; Transformer architecture; Financial relationship analysis; Attention mechanisms; Fraud detection; Heterogeneous networks

CITE THIS PAPER

Laura Chen, Robert Murphy. Interpretable transformer models for relationship analysis in financial data. AI and Data Science Journal. 2025, 2(2): 35-41. DOI: https://doi.org/10.61784/adsj3023.

REFERENCES

[1] George A S. Finance 4.0: The transformation of financial services in the digital age. Partners Universal Innovative Research Publication, 2024, 2(3): 104-125.

[2] Zhang Q, Chen S, Liu W. Balanced Knowledge Transfer in MTTL-ClinicalBERT: A Symmetrical Multi-Task Learning Framework for Clinical Text Classification. Symmetry, 2025, 17(6): 823.

[3] Shao Z, Wang X, Ji E, et al. GNN-EADD: Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning. IEEE Access, 2025.

[4] Ji E, Wang Y, Xing S, Jin J. Hierarchical Reinforcement Learning for Energy-Efficient API Traffic Optimization in Large-Scale Advertising Systems. IEEE Access, 2025.

[5] Jin J, Xing S, Ji E, et al. XGate: Explainable Reinforcement Learning for Transparent and Trustworthy API Traffic Management in IoT Sensor Networks. Sensors (Basel, Switzerland), 2025, 25(7): 2183.

[6] Cao J, Zheng W, Ge Y, et al. DriftShield: Autonomous fraud detection via actor-critic reinforcement learning with dynamic feature reweighting. IEEE Open Journal of the Computer Society, 2025.

[7] Wang J, Liu J, Zheng W, et al. Temporal Heterogeneous Graph Contrastive Learning for Fraud Detection in Credit Card Transactions. IEEE Access, 2025.

[8] Mai N T, Cao W, Liu W. Interpretable Knowledge Tracing via Transformer-Bayesian Hybrid Networks: Learning Temporal Dependencies and Causal Structures in Educational Data. Applied Sciences, 2025, 15(17): 9605.

[9] Sun T, Yang J, Li J, et al. Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access, 2024.

[10] Cao W, Mai N T, Liu W. Adaptive knowledge assessment via symmetric hierarchical Bayesian neural networks with graph symmetry-aware concept dependencies. Symmetry, 2025, 17(8): 1332.

[11] Mai N T, Cao W, Wang Y. The global belonging support framework: Enhancing equity and access for international graduate students. Journal of International Students, 2025, 15(9): 141-160.

[12] Tan Y, Wu B, Cao J, et al. LLaMA-UTP: Knowledge-Guided Expert Mixture for Analyzing Uncertain Tax Positions. IEEE Access, 2025.

[13] Mattsson C. Financial Transaction Networks to Describe and Model Economic Systems. Doctoral dissertation, Northeastern University, 2020.

[14] Olushola A, Mart J. Fraud detection using machine learning. ScienceOpen Preprints, 2024.

[15] Mareedu A. AI-Driven Security for Financial Transactions: Leveraging LLMs, Federated Learning, and Behavioral Biometrics. International Journal of Emerging Research in Engineering and Technology, 2024, 5(4): 62-73.

[16] Popoola N T, Bakare F A. Advanced computational forecasting techniques to strengthen risk prediction, pattern recognition, and compliance strategies. 2024.

[17] Ali M A. Does the online card payment system unwittingly facilitate fraud? Doctoral dissertation, Newcastle University, 2019.

[18] Neupane S, Ables J, Anderson W, et al. Explainable intrusion detection systems (x-ids): A survey of current methods, challenges, and opportunities. IEEE Access, 2022, 10: 112392-112415.

[19] Dritsas E, Trigka M. Exploring the intersection of machine learning and big data: A survey. Machine Learning and Knowledge Extraction, 2025, 7(1): 13.

[20] Popoola N T. Big data-driven financial fraud detection and anomaly detection systems for regulatory compliance and market stability. International Journal of Computer Applications and Technology Research, 2023, 12(09): 32-46.

[21] Serrano S, Smith N A. Is attention interpretable? arXiv preprint arXiv:1906.03731, 2019.

[22] Galassi A, Lippi M, Torroni P. Attention in natural language processing. IEEE transactions on neural networks and learning systems, 2020, 32(10): 4291-4308.

[23] Vrahatis A G, Lazaros K, Kotsiantis S. Graph attention networks: a comprehensive review of methods and applications. Future Internet, 2024, 16(9): 318.

[24] Carvalho D V, Pereira E M, Cardoso J S. Machine learning interpretability: A survey on methods and metrics. Electronics, 2019, 8(8): 832.

[25] Oko-Odion C. AI-Driven Risk Assessment Models for Financial Markets: Enhancing Predictive Accuracy and Fraud Detection. International Journal of Computer Applications Technology and Research, 2025, 14(04): 80-96.

[26] Zheng W, Liu W. Symmetry-Aware Transformers for Asymmetric Causal Discovery in Financial Time Series. Symmetry, 2025.

[27] Cross C, Gillett R. Exploiting trust for financial gain: An overview of business email compromise (BEC) fraud. Journal of Financial Crime, 2020, 27(3): 871-884.