Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201308,
        author = {Muthu Kumar PK and Raja Surya R and Sajeiv Rawyar AA and Muthumari L},
        title = {Explainable Al-Driven Anti-Money laundering an Transaction Risk Management Framework Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {3686-3693},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201308},
        abstract = {Financial institutions are struggling to identify and prevent money laundering practices because cases are becoming complex and the amount of money handling through financial institutions is increasing day-by-day. Traditional rule-based systems for monitoring are often incapable of detecting evolving fraud patterns and are limited in their degree of decision-making transparency. This research proposes an explainable artificial intelligence-driven framework for anti-money laundering and managing risk of transactions by using machine learning and synthetic transaction data. The framework combines a transaction monitoring mechanism with a risk prediction mechanism and explainability mechanisms based on machine learning to detect suspicious financial behavior. A hybrid detection strategy of predictive and rule based analysis is implemented to assess attributes related to transactions such as transaction amount, time characteristics, and type of transaction. Synthetic transaction generation is used to simulate realistic financial behavior for assisting the training and testing of financial models in an environment in which real financial data is limited. The framework computes a risk score for every single transaction and classifies every transaction as normal or suspicious depending on the predictive probabilities and threshold values To improve transparency and interpretability, explainable artificial intelligence techniques are introduced to analyse the contribution of individual features for fraud detection results. The system further includes automated alert generation and monitoring dashboards to help compliance officers efficiently go through high-risk transactions. Experimental analysis shows that the proposed framework can be effectively used to identify suspicious transaction patterns and at the same time preserve interpretability and operational transparency. The combination of machine learning, synthetic data generation and AI explainability offers a feasible and scalable way in which financial institutions can build stronger anti-money laundering monitoring systems and deliver improved risk management abilities in digital financial areas.},
        keywords = {Anti Money Laundering, Explainable Artificial Intelligence, Machine Learning, Transaction Risk Management, Detecting Fraud, Synthetic Transaction data, Risk Scoring, Financial Transaction Monitoring, Detecting Suspicious Transactions, Financial Compliance Systems.},
        month = {May},
        }