IDEAS home Printed from https://ideas.repec.org/a/gvu/tcsst0/v8y2026i3id2361.html

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

Author

Listed:
  • Ravi N.
  • Sathiamoorthy S.

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.

Suggested Citation

Handle: RePEc:gvu:tcsst0:v:8:y:2026:i:3:id:2361
DOI: 10.36548/jtcsst.2026.3.017
as

Download full text from publisher

File URL: https://irojournals.com/tcsst/article/view/2361
File Function: Abstract page
Download Restriction: no

File URL: https://irojournals.com/tcsst/article/download/2361/2166
File Function: Full text
Download Restriction: no

File URL: https://libkey.io/10.36548/jtcsst.2026.3.017?utm_source=ideas
LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
---><---

More about this item

Keywords

;
;
;
;
;
;

Statistics

Access and download statistics

Corrections

All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gvu:tcsst0:v:8:y:2026:i:3:id:2361. See general information about how to correct material in RePEc.

If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

We have no bibliographic references for this item. You can help adding them by using this form .

If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Manager (email available below). General contact details of provider: https://irojournals.com/tcsst .

Please note that corrections may take a couple of weeks to filter through the various RePEc services.

IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.