R. Lingeswari
S. Brindha
- Ph.D Research Scholar Department of Computer Science, St.Peter’s Institute of Higher Education & Research, Chennai Tamil Nadu India
- Associate Professor Department of Computer Applications, St.Peter’s Institute of Higher Education & Research, Chennai Tamil Nadu India
Abstract
This article discusses the use of machine learning algorithms to discover firms that are prone to money laundering. The purpose of this research is to develop, describe, and test a machine learning model for determining which bank transactions should be physically scrutinized for money laundering activities. To train a supervised machine learning model, three categories of historical data are required: legitimate “normal” transactions, transactions flagged as suspicious by the bank’s internal alert system, and instances of suspected money laundering reported to authorities. The model is trained to use various data sources, including background details of both the sender and receiver, past behaviors, and transaction records, to predict the likelihood that a new transaction warrants reporting. Our newly designed procedure outperforms the bank’s current methodology in terms of a fair assessment of performance. This research represents one of the scarce published anti-money laundering (AML) models for identifying suspicious transactions that has been tested on a dataset of realistic size. In addition, the paper provides a new performance indicator that was created particularly to compare the proposed solution against the bank’s existing anti-money laundering system. The greatest quality prediction results are obtained when a gradient boosting method is used instead of decision trees. The speed at which the optimal set might be produced was determined using the hyperopt and optima Python packages, and the quality of hyper parameter selection was studied. The model makes it possible to compile a list of the most crucial indicators for the early detection of money laundering and terrorist financing (ML/TF) organizations, and also provides appropriate suggestions for enhancing the compliance control process. Monetary laundering is a result of corruption, illegal activities, and organized crime, all of which have a social effect and have embroiled numerous groups, both directly and indirectly, in the laundering of illicit cash via a number of methods. This paper suggests employing a machine learning method to identify potentially suspicious activities among non-banking correspondents. A non-banking correspondent is a kind of financial agent that executes financial transactions on behalf of particular banking customers. Our results show that certain ways are more suited to this circumstance than others, and that these methodologies make it simpler to spot irregularities and suspicious transactions in this kind of financial intermediary.
Keywords: Anti-Money Laundering (AML), Machine Learning, Terrorist Financing
[This article belongs to Current Trends in Information Technology(ctit)]
References
References
[1] Jullum M, Løland A, Huseby RB, Ånonsen G, Lorentzen J. Detecting money laundering transactions with machine learning. Journal of Money Laundering Control. 2020 Jan 21;23(1):173-86.
[2] Dr.S.Brindha and T.Ajisha, “ An Efficient Ensemble Classifier for Heart Disease Diagnosis and early Prediction”, International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-9 Issue-4, PP 109-114, November 2020.
[3] Bayona-Rodríguez H. Money laundering in rural areas with illicit crops: empirical evidence for Colombia. Crime, Law and Social Change. 2019 Nov;72(4):387-417.
[4] Ali MZ, Shabbir MN, Liang X, Zhang Y, Hu T. Machine learning-based fault diagnosis for single-and multi-faults in induction motors using measured stator currents and vibration signals. IEEE Transactions on Industry Applications. 2019 Jan 27;55(3):2378-91.
[5] BRINDHA M, Sakthivel NK, SUBASREE S. Virtual Machine Dynamic Migration Strategy based Intelligent Flow Forecast Technique for Cloud Data Centers. International Journal of Emerging Technologies and Innovative Research (IJETIR). 2019 Apr;6(4):368-76.
[6] Rao AA, Kanchana V. Dynamic approach for detection of suspicious transactions in money laundering. International Journal of Engineering & Technology. 2018;7(3):10-3.
[7] R.Lingeswari and Dr.S.Brindha “ validation of Block chain transaction in banking sector” Humanities and Social Science studies, VOL. 12 ISSUE (1) NO 09 JANUARY – JUNE : 2023, ISSN 2319-829X
[8] R.Lingeswari and Dr.S.Brindha “ Identification of Vulnerability During Cross Border Transaction in IoT” Jounal of Harbin Engineering University. ISSN-1006-7043 , Vol 44 No 9 Issue September ,2023.
[9] Chen T, Guestrin C. Xgboost: A scalable tree boosting system. InProceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 785-794).
[10] Alexandre C, Balsa J. Client profiling for an anti-money laundering system. arXiv preprint arXiv:1510.00878. 2015 Oct 3.
[11] Colladon AF, Remondi E. Using social network analysis to prevent money laundering. Expert Systems with Applications. 2017 Jan 1;67:49-58.
[12] Bholowalia P, Kumar A. EBK-means: A clustering technique based on elbow method and k-means in WSN. International Journal of Computer Applications. 2014 Jan 1;105(9).
[13] Lacoste A, Larochelle H, Laviolette F, Marchand M. Sequential model-based ensemble optimization. arXiv preprint arXiv:1402.0796. 2014 Feb 4.
[14] Bergstra J, Bardenet R, Bengio Y, Kégl B. Algorithms for hyper-parameter optimization. Advances in neural information processing systems. 2011;24.
[15] R.Lingeswari and Dr.S.Brindha “ Analysing and classification of Attacks in Financial Transactions using Machine Learning”, Inter National Conference on Innovative Technologies and their Applications in Higher Education-Science. ISBN No. 978-93-92042-31-7, October 2022.
[16] Adankon MM, Cheriet M. Support vector machine. Encyclopedia of biometrics. 2009:1303-8.
[17] Bolton RJ, Hand DJ. Statistical fraud detection: A review. Statistical science. 2002 Aug;17(3):235-55.
[18] Breiman L. Random Forests. 2001 Jan. Available from: https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf
Current Trends in Information Technology
| Volume | 14 |
| Issue | 02 |
| Received | February 29, 2024 |
| Accepted | April 25, 2024 |
| Published | July 3, 2024 |