search for




 

Detecting Hawala for funding terrorism and data mining
Journal of the Korean Data & Information Science Society 2024;35:179-94
Published online March 31, 2024;  https://doi.org/10.7465/jkdi.2024.35.2.179
© 2024 Korean Data and Information Science Society.

Ki-Joune Li1 · Marzhan Alenova2

1Department of Computer Science and Engineering, Pusan National University
2Gaia3D
Correspondence to: This research was supported by a 2-year Research Grant of Pusan National University.
1 Professor, Department of Computer Science and Engineering, Pusan National University, Pusan 46241, Korea. E-mail: lik@pnu.edu
2 Researcher, Gaia3d, Seoul 08512, Korea.
Received January 12, 2024; Revised February 27, 2024; Accepted March 4, 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Hawala is a traditional banking system for money transfer, which is considered as illegal. It has been used for money laundering, in particularly for funding terrorists. Many international agencies such as Interpol and FATF have been working to detect financing terrorists including Hawala. However, these efforts mostly rely on manual investigations, which take a considerable amount of time and resources. In this paper, we discuss the following several issues the automation of detecting Hawala by data mining to improve the investigation process of law enforcement agencies. First, we present main typologies of Hawala transaction for terrorist funding, which will serve as functional requirements for data mining methods. Second, we discuss the issue of data availability of bank transactions due to its confidentiality requirement and propose a data augmentation method to overcome this constraint. Third, we suggest a data mining method for detecting the basic typology of Hawala and show its performance by experiments. We expect that this work is a first step toward the automation of Hawala detection for funding terrorists, although the funding methods for terrorist groups constantly evolve using new technologies.
Keywords : Funding terrorists, hawala, hawala data augmentation, hawala data mining, hawala typologies