Browse > Article

Scoring models to detect foreign exchange money laundering  

Hong, Seong-Ik (Dept. of Computer Science & Industrial System Engineering, Yonsei University)
Moon, Tae-Hee (Dept. of Computer Science & Industrial System Engineering, Yonsei University)
Sohn, So-Young (Dept. of Computer Science & Industrial System Engineering, Yonsei University)
Publication Information
IE interfaces / v.18, no.3, 2005 , pp. 268-276 More about this Journal
Abstract
In recent years, the money Laundering crimes are increasing by means of foreign exchange transactions. Our study proposes four scoring models to provide early warning of the laundering in foreign exchange transactions for both inward and outward remittances: logistic regression model, decision tree, neural network, and ensemble model which combines the three models. In terms of accuracy of test data, decision tree model is selected for the inward remittance and an ensemble model for the outward remittance. From our study results, the accumulated number of transaction turns out to be the most important predictor variable. The proposed scoring models deal with the transaction level and is expected to help the bank teller to detect the laundering related transactions in the early stage.
Keywords
scoring; foreign exchange laundering detection; data mining;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Chen, M.e., & Huang, S.H. (2003), Credit scoring and rejected instances reassigning through evolutionary computation techniques. Expert System with Applications, 24, 433-441   DOI   ScienceOn
2 Desai,V., Crook,J., & Overstreet, G. (1996), A comparison of neural networks and linear scoring models in credit union environment. European Journal of Operations Management, 95, 24-37   DOI   ScienceOn
3 Kim, S.B.(200 1), A Study on the Characteristic of Credit Cards Customer for Building Credit Scoring System, Korea Univ., M.S. thesis, Korea
4 Kim, Y.S. & Sohn, S. y. (2003), Managing loan customers using misclassification patterns of credit scoring model. Expert system with Applications 57(10),482-488
5 Koker, I. (2002), Money Laundering Trends in South Africa. Journal of Money Laundering Control, 6( 1), 27 -41   DOI   ScienceOn
6 Kuo-Ellen (2002), Fraud In Documentary Credit Transaction. Journal of Money Laundering Control, 5(3), 192-207   DOI   ScienceOn
7 Sohn, SY & Shin, H.W.$(1997)^{a}$, Data Mining for Road Traffic Accident Type Classification, Korean Society of Transportation. 6(4), pp.187-194
8 Westphal, e. (998), Data Mining Solutions. John Wiley and Sons, New York, USA
9 Berry, M.J .. & Linoff, G. (1997), Data Mining Techniques. John Wiley and Sons, New York, USA
10 Buchanan, B. (2004), Money laundering global obstacle. Research in International Business and Finance, 18, 115-127   DOI   ScienceOn
11 Rahman, F. & Sheikn, A. (2002), The Underground Banking Systems and their Impact on Control of Money Laundering. Journal of Money laundering Control, 6(1), 42-45   DOI   ScienceOn
12 Jung, S'y'(2002), A study of Visual Data Mining Based on link Analysis for insurance Fraud detection, Soogsil Univ., M.S. thesis, Korea
13 Lee, S.B.(2001), Logistic Analsys for Credit Scoring, Sookmyung Women's Univ., M.S. thesis, Korea
14 Philippsohn, S. (2001), Money Laundering on the Internet. Computers & Security, 20, 485-490   DOI   ScienceOn
15 Sohn, S.Y & Shin, H.W.$(1997)^{b}$, Comparison of Data Mining Classification Algorithms for Categorical Feature Variables, 12(4), 551- 556
16 Kang,H.e., Han, S.T. Choi, J.H., Kim, £.S., & Kim, M.K.(2002), Methodology and Application of Data Mining, Freedom Academy, Seoul, Korea
17 Jo, D.H.(1993), A study of Management of Foreign Money in Korea, Hankuk Univ. of Foreign Studies., M.S. thesis, Korea
18 Kim, J.S.(2001), Credit Scoring Model Using Bayesian Method, Korea Univ., M.S. thesis, Korea
19 Rezaee, Z. (2003), Causes, consequences, and deterence of financial statement fraud. Critical Perspectives on Accounting, 16(3), 277-298   DOI   ScienceOn