Realistic Synthetic Financial Transactions for Anti-Money Laundering Models

被引:0
作者
Altman, Erik [1 ]
Blanusa, Jovan [2 ]
von Niederhausern, Luc [2 ]
Egressy, Beni [3 ]
Anghel, Andreea [2 ]
Atasu, Kubilay [2 ]
机构
[1] IBM Watson Res, Yorktown Hts, NY 10598 USA
[2] IBM Res Europe, Zurich, Switzerland
[3] Swiss Fed Inst Technol, Zurich, Switzerland
来源
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023) | 2023年
基金
瑞士国家科学基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the widespread digitization of finance and the increasing popularity of cryptocurrencies, the sophistication of fraud schemes devised by cybercriminals is growing. Money laundering - the movement of illicit funds to conceal their origins - can cross bank and national boundaries, producing complex transaction patterns. The UN estimates 2-5% of global GDP or $0.8 - $2.0 trillion dollars are laundered globally each year. Unfortunately, real data to train machine learning models to detect laundering is generally not available, and previous synthetic data generators have had significant shortcomings. A realistic, standardized, publicly-available benchmark is needed for comparing models and for the advancement of the area. To this end, this paper contributes a synthetic financial transaction dataset generator and a set of synthetically generated AML (Anti-Money Laundering) datasets. We have calibrated this agent-based generator to match real transactions as closely as possible and made the datasets public. We describe the generator in detail and demonstrate how the datasets generated can help compare different machine learning models in terms of their AML abilities. In a key way, using synthetic data in these comparisons can be even better than using real data: the ground truth labels are complete, whilst many laundering transactions in real data are never detected.
引用
收藏
页数:24
相关论文
共 50 条
[21]   Anti-money laundering regulations and financial inclusion: empirical evidence across the globe [J].
Ofoeda, Isaac .
JOURNAL OF FINANCIAL REGULATION AND COMPLIANCE, 2022, 30 (05) :646-664
[22]   Research On Anti-Money Laundering Hierarchical Model [J].
Jin, Yaqin ;
Qu, Zhenxin .
PROCEEDINGS OF 2018 IEEE 9TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS), 2018, :406-411
[23]   Anti-money laundering regulation and the art market [J].
Hufnagel, Saskia ;
King, Colin .
LEGAL STUDIES, 2020, 40 (01) :131-150
[24]   Anti-money laundering supervision by intelligent algorithm [J].
Yang, Guangyi ;
Liu, Xiaoxing ;
Li, Beixin .
COMPUTERS & SECURITY, 2023, 132
[25]   The agency dilemma in anti-money laundering regulation [J].
Naheem, Mohammed Ahmad .
JOURNAL OF MONEY LAUNDERING CONTROL, 2020, 23 (01) :26-37
[26]   Protecting Forests Through Anti-Money Laundering [J].
不详 .
FORESTRY CHRONICLE, 2010, 86 (04) :411-411
[27]   Development of anti-money laundering regime in Russia [J].
Subbotina, Natalya .
JOURNAL OF MONEY LAUNDERING CONTROL, 2008, 11 (04) :358-+
[28]   The role of foundations in international anti-money laundering [J].
Muller, Wouter H. .
TRUSTS & TRUSTEES, 2007, 13 (05) :135-143
[29]   Particularities of anti-money laundering methods in football [J].
Cindori, Sonja ;
Manola, Ana .
JOURNAL OF MONEY LAUNDERING CONTROL, 2020, 23 (04) :885-897
[30]   Anti-money laundering under Turkish law [J].
Okuyucu, Gunes .
JOURNAL OF MONEY LAUNDERING CONTROL, 2009, 12 (01) :88-+