IRO Journals
Journal of Trends in Computer Science and Smart Technology

XAI-Guided Features with Neural Learning Architecture for Anti-Money Laundering Detection in Financial Transactions

Open Access
Published: 29 July, 2026
Pages: 768-790
  • Ravi N. , Ravi N.
    Department of Computer and Information Science, Annamalai University, Annamalai Nagar, India
    Department of Computer and Information Science, Annamalai University, Annamalai Nagar, India
  • Sathiamoorthy S. Sathiamoorthy S.
    Department of Computer and Information Science, Annamalai University, Annamalai Nagar, India
    Department of Computer and Information Science, Annamalai University, Annamalai Nagar, India
view PDF
view PDF

How to Cite

N., Ravi, and Sathiamoorthy S. 2026. “XAI-Guided Features With Neural Learning Architecture for Anti-Money Laundering Detection in Financial Transactions”. Journal of Trends in Computer Science and Smart Technology 8 (3): 768-90. https://doi.org/10.36548/jtcsst.2026.3.017.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Anti-Money Laundering
Class Imbalance
Fraud Detection
Explainable Artificial Intelligence
Feature Learning
Baseline Model

Abstract

Anti-Money Laundering (AML) involves concealing the origin of illegal money through financial crime and the necessity for nations and institutions to develop and implement AML measures. Machine learning (ML) have shown efficiency in detecting suspicious transactions; nonetheless, they do not capture complex non-linear behavior from transactions while maintaining transparency and reliability. In addition, the black box nature of deep learning techniques makes them unsuitable for real-time implementation in financial security applications, as they require transparent decision-making. To address this problem, the current research proposes XAIGFL-NN for Robust AML Detection. The model is designed for integrating domain-aware feature engineering, minority class-preserving sampling, and explainable neural learning to detect suspicious transactions in a large-scale financial environment. A neural network that has been fine-tuned through RMSprop is used to learn discriminatory transaction representations, and SHAP-based interpretability is applied to discover significant transaction features to improve the learning of feature significance. Different from conventional XAI models that utilize explainability for interpretability purposes only, the proposed approach leverages SHAP-based feature engineering to improve both model interpretability and anomaly detection capability. The approach is tested on two popular benchmark datasets, namely IBM AMLSim and PaySim, both of which have heavily skewed class distributions. Extensive comparative outcomes report the encouraging performance of the XAIGFL-NN algorithm over recent methodologies. Therefore, the proposed model is found to be an accurate, interpretable, and robust solution for next-generation AML and financial transaction intelligence systems.

References

  1. Amoako, Elizabeth Kuukua Woode, Victor Boateng, Ola Ajay, Tobias Kwame Adukpo, and Nicholas Mensah. "Exploring the Role of Machine Learning and Deep Learning in Anti-Money Laundering (AML) Strategies Within US Financial Industry: A Systematic Review of Implementation, Effectiveness, and Challenges." Finance & Accounting Research Journal 7, no. 1 (2025): 22-36.
  2. Bi, Wenyu, Toan Khang Trinh, and Shukai Fan. "Machine Learning-based Pattern Recognition for Anti-Money Laundering in Banking Systems." Journal of Advanced Computing Systems 4, no. 11 (2024): 30-41.
  3. Pazos, Jorge Felix Martínez, Jorge Gulín González, David Batard Lorenzo, and Jorge Alejandro Robaina Morales. "Fraud Transaction Detection for Anti-Money Laundering Systems based on Deep Learning." Journal of Emerging Computer Technologies 3, no. 1 (2024): 29-34.
  4. Bakry, Ahmed N., Almohammady S. Alsharkawy, Mohamed S. Farag, and Kamal R. Raslan. "Automatic Suppression of False Positive Alerts in Anti-Money Laundering Systems Using Machine Learning: AN Bakry et al." The Journal of Supercomputing 80, no. 5 (2024): 6264-6284.
  5. Konstantinidis, Giannis, and Alexander Gegov. "Deep Neural Networks for Anti Money Laundering Using Explainable Artificial Intelligence." In 2024 IEEE 12th international conference on intelligent systems (IS), IEEE, 2024, 1-6.
  6. Iguodala, O., and Aghogho Oyiborhoro. "AI-Powered Anti-Money Laundering (AML) and Fraud Detection-Enhancing Financial Security Through Intelligent Fraud Detection." World Journal of Advanced Research and Reviews 26 (2025): 3702-3714.
  7. Oztas, Berkan, Deniz Cetinkaya, Festus Adedoyin, Marcin Budka, Gokhan Aksu, and Huseyin Dogan. "Transaction Monitoring in Anti-Money Laundering: A Qualitative Analysis and Points of View from Industry." Future Generation Computer Systems 159 (2024): 161-171.
  8. Olaniyi, Oluwadayo Mafolasere, Ifesinachi Stephen Aroh, Henry Onyii, Olufunke Cynthia Metibemu, and Oluwaseun Ibrahim Akinola. "Graph Neural Networks for Multi-Layered Financial Crime Network Detection: An Explainable AI Framework for Anti-Money Laundering." Journal of Engineering Research and Reports 28, no. 2 (2026): 18-36.
  9. Lin, Ziqian, Qining Luo, Dongze Wu, Jie Shen, Lingying Li, Xunyi Nong, and Zhenkai Qin. "Detecting Illicit Transactions in Bitcoin: A Wavelet-Temporal Graph Transformer Approach for Anti-Money Laundering." Scientific Reports 16, no. 1 (2026): 1548.
  10. Sidiq, Mashkhal Abdalwahid, and Yimamu Kirubel Wondaferew. "Anti-Money Laundering Systems Using Deep Learning." arXiv preprint arXiv:2509.19359 (2025).
  11. Wang, Qianyu, Wei-Tek Tsai, and Bowen Du. "RMGANets: Reinforcement Learning-Enhanced Multi-Relational Attention Graph-Aware Network for Anti-Money Laundering Detection." Complex & Intelligent Systems 11, no. 1 (2025): 5.
  12. Wu, You, Ying Qin, Xin Su, and Yuxiu Lin. "Transformer-based Risk Monitoring for Anti-Money Laundering with Transaction Graph Integration." In Proceedings of the 2025 2nd International Conference on Digital Economy, Blockchain and Artificial Intelligence, 2025, 388-393.
  13. Yu, Qian, Zhen Xu, and Zong Ke. "Deep Learning for Cross-Border Transaction Anomaly Detection in Anti-Money Laundering Systems." In 2024 6th International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), IEEE, 2024, 244-248.
  14. Wan, Fei, and Ping Li. "A Novel Money Laundering Prediction Model based on a Dynamic Graph Convolutional Neural Network and Long Short-Term Memory." Symmetry 16, no. 3 (2024): 378.
  15. Rajath Karangara, Saikiran Subbagari, "Filtering and Detection of Anti Money Laundering with the Aid of Optimization-Enabled Machine Learning Techniques," International Journal of Computer & Organization Trends (IJCOT), vol. 14, no. 1, 2024, 1-11.
  16. https://www.kaggle.com/datasets/anshankul/ibm-amlsim-example-dataset
  17. https://www.kaggle.com/datasets/ealaxi/paysim1
  18. Zhou, Wensheng, Chen Liu, Peng Yuan, and Lei Jiang. "An Undersampling Method Approaching the Ideal Classification Boundary for Imbalance Problems." Applied Sciences 14, no. 13 (2024): 5421.
  19. Haq, Hafiz Burhan Ul, Rabia Younis, and Muhammad Shujat Ali. "Towards Robust Network Security: Evaluating Machine Learning Algorithms for Intrusion Detection." Decision Making Advances 3, no. 1 (2025): 126-138.
  20. Björnsson, Ola, and Per Tunestål. "Knock Detection with Ion Current and Vibration Sensor: A Comparative Study of Logistic Regression and Neural Networks." Energies 17, no. 22 (2024): 5693.
  21. Mondal, Subhash, Ranjan Maity, and Amitava Nag. "An Efficient Artificial Neural Network-Based Optimization Techniques for the Early Prediction of Coronary Heart Disease: Comprehensive Analysis." Scientific Reports 15, no. 1 (2025): 4827.
  22. Zhu, Wenbing, Shihan Luo, Hyowon Lee, Amandeep Singh, and Siby Samuel. "Lightweight and Interpretable Transformer-Based Models for Predicting Driving Comfort in Autonomous Vehicles." IEEE Access 14 (2026): 9435-9452.
  23. RAJA, MAMUNUR R., Md Anwar Hosen, Md Farhad Kabir, Sharmin Sultana, Shah Ahammadullah Ashraf, and Rakibul Islam. "Detecting and Preventing Money Laundering Using Deep Learning and Graph Analysis." International Journal of Advanced Computer Science & Applications 16, no. 6 (2025).
  24. Li, Xiang, Lei Chu, Yujun Li, Zhanjun Xing, Fengqian Ding, Jintao Li, and Ben Ma. "An Intelligent Financial Fraud Detection Support System Based on Three-Level Relationship Penetration." Mathematics 12, no. 14 (2024): 2195.
  25. Yang, Yiwen, Chengjun Xu, and Guisheng Tian. "Lightweight Financial Fraud Detection Using a Symmetrical GAN-CNN Fusion Architecture." Symmetry 17, no. 8 (2025): 1366.