學術產出-Theses
Article View/Open
Publication Export
-
題名 機器學習在證券業反洗錢監控之應用
Applying Machine Learning on Anti-Money Laundering Detection in Securities Firms作者 蘇志祐
Su, Zhi-You貢獻者 何靜嫺
Ho, Shirley J.
蘇志祐
Su, Zhi-You關鍵詞 洗錢防制
K-means分群演算法
支援向量機
異常檢測
疑似洗錢交易態樣
證券業
Anti-money laundering
K-means
Support vector machine
Anomaly detection
Suspicious types
Securities industry日期 2022 上傳時間 10-Feb-2022 13:10:36 (UTC+8) 摘要 本文為研究機器學習在證券業反洗錢交易監控的實證分析。利用台灣一家證券公司提供的實際交易數據，我們研究並比較了傳統監控方法和基於兩種機器學習演算法的監控方法：K-means分群演算法和支援向量機。我們選擇了台灣金融監督委員會與台灣證券公會研議後發布之兩類疑似洗錢或資恐交易態樣來比較監控結果。我們的分析揭示了機器學習演算法在監測洗錢方面的潛在優勢，結果顯示，機器學習算法在監控率(DR)方面優於傳統的監控方法。本文對機器學習在證券業反洗錢交易監控中的應用提供了深入的研究。
This paper studies the empirical analysis of machine learning for money laundering detection algorithms in the securities industry. Using actual transaction data provided by a securities firm in Taiwan, we study and compare the traditional detection method with detection methods based on two machine learning algorithms: K-means and support vector machine. We choose two types of suspicious types of transactions suggesting money laundering approved by the Financial Supervisory Commission in Taiwan to compare the detection results. Our analysis reveals the potential advantages of machine learning algorithms in monitoring money laundering, and the results show that machine learning algorithms outperform the traditional detection method in terms of detection rates. This paper provides insights into the application of machine learning in money laundering detection in the securities industry.參考文獻 1.Anti-Money Laundering Division (AMLD) (2017). Anti-Money Laundering Annual Report, 2017.2.Anti-Money Laundering Division (AMLD) (2018). Anti-Money Laundering Annual Report, 2018.3.Anti-Money Laundering Division (AMLD) (2019). Anti-Money Laundering Annual Report, 2019.4.Anti-Money Laundering Office, Executive Yuan (2018, May). National Money Laundering and Terrorist Financing Risk Assessment Report.5.Asia/Pacific Group on Money Laundering (2019). Mutual Evaluation Report of Chinese Taipei.6.Ben-Gal, I. (2005). Outlier detection. In Data mining and knowledge discovery handbook (pp. 131-146). Springer, Boston, MA.7.Bolton, R. J., and Hand, D. J. (2002). Statistical fraud detection: A review. Statistical science, 17(3), 235-255.8.Boser, B. E., Guyon, I. M., and Vapnik, V. N. (1992, July). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152).9.Breslow, S., Hagstroem, M., Mikkelsen, D., and Robu, K. (2017). The new frontier in anti–money laundering. McKinsey and Company, November.10.Chen, Z., Teoh, E. N., Nazir, A., Karuppiah, E. K., and Lam, K. S. (2018). Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection: a review. Knowledge and Information Systems, 57(2), 245-285.11.Cortes, C., and Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.12.Dreżewski, R., Sepielak, J., and Filipkowski, W. (2015). The application of social network analysis algorithms in a system supporting money laundering detection. Information Sciences, 295, 18-32.13.European Commission (2021). Proposal for a Regulation establishing the Authority for Anti-Money Laundering and Countering the Financing of Terrorism and amending Regulations (EU) No 1093/2010, (EU) 1094/2010, (EU) 1095/2010.14.Fenergo officials (2018). Firms Fined $26B Over the Past Decade: Fenergo.15.Financial Action Task Force on Money Laundering (FATF) (2009). Money Laundering and Terrorist Financing in the Securities Sector.16.Financial Action Task Force on Money Laundering (FATF) (2012). FATF Recommendations 2012.17.Financial Examination Bureau, FSC (2017). Template for Guidelines Governing Anti-Money Laundering and Countering Terrorism Financing of Securities Firms.18.Financial Supervisory Commission (2017). Regulations Governing Anti-Money Laundering of Financial Institutions.19.Gao, Z., and Ye, M. (2007). A framework for data mining-based anti-money laundering research. Journal of Money Laundering Control, 10(2), 170-179.20.Garcia, E., Regan, P., Stern, J., Johnson, W., Macallister, R., Reidenberg, J., ... and Welling, S. (1995). Information Technologies for the Control of Money Laundering. OTA-ITC-630, Washington, DC.21.Hartigan, J. A. (1975). Clustering algorithms. John Wiley and Sons, Inc..22.Hartigan, J. A., and Wong, M. A. (1979). AK‐means clustering algorithm. Journal of the Royal Statistical Society: Series C (Applied Statistics), 28(1), 100-108.23.Hsu, C. W., Chang, C. C., and Lin, C. J. (2003). A practical guide to support vector classification.24.Hubert, M., and Vandervieren, E. (2008). An adjusted boxplot for skewed distributions. Computational statistics and data analysis, 52(12), 5186-5201.25.Keerthi, S. S., and Lin, C. J. (2003). Asymptotic behaviors of support vector machines with Gaussian kernel. Neural computation, 15(7), 1667-1689.26.Keyan, L., and Tingting, Y. (2011, November). An improved support-vector network model for anti-money laundering. In 2011 Fifth International Conference on Management of e-Commerce and e-Government (pp. 193-196). IEEE.27.Kingdon, J. (2004). AI fights money laundering. IEEE Intelligent Systems, 19(3), 87-89.28.Kirkland, J. D., Senator, T. E., Hayden, J. J., Dybala, T., Goldberg, H. G., and Shyr, P. (1999). The nasd regulation advanced-detection system (ads). AI Magazine, 20(1), 55-55.29.Le Khac, N. A., and Kechadi, M. T. (2010, December). Application of data mining for anti-money laundering detection: A case study. In 2010 IEEE International Conference on Data Mining Workshops (pp. 577-584). IEEE.30.Le-Khac, N. A., Markos, S., and Kechadi, M. T. (2009, September). Towards a new data mining-based approach for anti-money laundering in an international investment bank. In International Conference on Digital Forensics and Cyber Crime (pp. 77-84). Springer, Berlin, Heidelberg.31.LexisNexis (2020). Global True Cost of Compliance 2020 report.32.LexisNexis Risk Solutions (2018). 2018 True Cost of AML Compliance report for the United States.33.Lin, H. T., and Lin, C. J. (2003). A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods. submitted to Neural Computation, 3(1-32), 16.34.Liu, R., Qian, X. L., Mao, S., and Zhu, S. Z. (2011, May). Research on anti-money laundering based on core decision tree algorithm. In 2011 Chinese Control and Decision Conference (CCDC) (pp. 4322-4325). IEEE.35.Liu, X., Zhang, P., and Zeng, D. (2008, June). Sequence matching for suspicious activity detection in anti-money laundering. In International conference on intelligence and security informatics (pp. 50-61). Springer, Berlin, Heidelberg.36.Mylevaganam, S. (2017). The Analysis of Human Development Index (HDI) for Categorizing the Member States of the United Nations (UN). Open Journal of Applied Sciences, 7(12), 661-690.37.Noble, J. C. (2021). 7. Money Laundering. In White-Collar and Financial Crimes (pp. 91-104). University of California Press.38.Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.39.Romaniuk, P., Haber, J., and Murray, G. (2007). Suspicious activity reporting. The CPA Journal, 77(3), 70.40.Senator, T. E., Goldberg, H. G., Wooton, J., Cottini, M. A., Khan, A. U., Klinger, C. D., ... and Wong, R. W. (1995). Financial crimes enforcement network AI system (FAIS) identifying potential money laundering from reports of large cash transactions. AI magazine, 16(4), 21-21.41.Syarif, I., Prugel-Bennett, A., and Wills, G. (2016). SVM parameter optimization using grid search and genetic algorithm to improve classification performance. Telkomnika, 14(4), 1502.42.Tan, P. N., Steinbach, M., and Kumar, V. (2016). Introduction to data mining. Pearson Education India.43.Tang, J., and Yin, J. (2005, August). Developing an intelligent data discriminating system of anti-money laundering based on SVM. In 2005 International conference on machine learning and cybernetics (Vol. 6, pp. 3453-3457). IEEE.44.Thorndike, R. L. (1953). Who belongs in the family?. Psychometrika, 18(4), 267-276.45.Umadevi, P., and Divya, E. (2012, December). Money laundering detection using TFA system. In International Conference on Software Engineering and Mobile Application Modelling and Development (ICSEMA 2012) (pp. 1-8). IET.46.United States Department of the Treasury (2015). National Money Laundering Risk Assessment.47.Wang, S. N., and Yang, J. G. (2007, August). A money laundering risk evaluation method based on decision tree. In 2007 international conference on machine learning and cybernetics (Vol. 1, pp. 283-286). IEEE.48.Watkins, R. C., Reynolds, K. M., Demara, R., Georgiopoulos, M., Gonzalez, A., and Eaglin, R. (2003). Tracking dirty proceeds: exploring data mining technologies as tools to investigate money laundering. Police Practice and Research, 4(2), 163-178.49.Zhang, Y., and Trubey, P. (2019). Machine learning and sampling scheme: An empirical study of money laundering detection. Computational Economics, 54(3), 1043-1063.50.Zhang, Z., Salerno, J. J., and Yu, P. S. (2003, August). Applying data mining in investigating money laundering crimes. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 747-752). 描述 碩士
國立政治大學
經濟學系
107258006資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107258006 資料類型 thesis dc.contributor.advisor 何靜嫺 zh_TW dc.contributor.advisor Ho, Shirley J. en_US dc.contributor.author (Authors) 蘇志祐 zh_TW dc.contributor.author (Authors) Su, Zhi-You en_US dc.creator (作者) 蘇志祐 zh_TW dc.creator (作者) Su, Zhi-You en_US dc.date (日期) 2022 en_US dc.date.accessioned 10-Feb-2022 13:10:36 (UTC+8) - dc.date.available 10-Feb-2022 13:10:36 (UTC+8) - dc.date.issued (上傳時間) 10-Feb-2022 13:10:36 (UTC+8) - dc.identifier (Other Identifiers) G0107258006 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/138955 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 經濟學系 zh_TW dc.description (描述) 107258006 zh_TW dc.description.abstract (摘要) 本文為研究機器學習在證券業反洗錢交易監控的實證分析。利用台灣一家證券公司提供的實際交易數據，我們研究並比較了傳統監控方法和基於兩種機器學習演算法的監控方法：K-means分群演算法和支援向量機。我們選擇了台灣金融監督委員會與台灣證券公會研議後發布之兩類疑似洗錢或資恐交易態樣來比較監控結果。我們的分析揭示了機器學習演算法在監測洗錢方面的潛在優勢，結果顯示，機器學習算法在監控率(DR)方面優於傳統的監控方法。本文對機器學習在證券業反洗錢交易監控中的應用提供了深入的研究。 zh_TW dc.description.abstract (摘要) This paper studies the empirical analysis of machine learning for money laundering detection algorithms in the securities industry. Using actual transaction data provided by a securities firm in Taiwan, we study and compare the traditional detection method with detection methods based on two machine learning algorithms: K-means and support vector machine. We choose two types of suspicious types of transactions suggesting money laundering approved by the Financial Supervisory Commission in Taiwan to compare the detection results. Our analysis reveals the potential advantages of machine learning algorithms in monitoring money laundering, and the results show that machine learning algorithms outperform the traditional detection method in terms of detection rates. This paper provides insights into the application of machine learning in money laundering detection in the securities industry. en_US dc.description.tableofcontents List of Tables 2List of Figures 31. Introduction 42. Related Literature 102.1 Traditional methods used in financial firms 102.2 Current AML solutions by machine learning techniques 113. Algorithms 133.1 K-means Clustering 143.2 Support Vector Machine 184. Data Source and Variables 204.1 Types of Suspicious Transactions 214.2 Risk Factors 225. Detection Results (Type No.3 Suspicious Transactions) 295.1 Traditional Detection Method 295.2 Machine Learning Methods (K-means、SVM) 316. Detection Results (Type No. 6 Suspicious Transactions) 406.1 Traditional Detection Method 406.2 Machine Learning Methods (K-means、SVM) 417. Concluding Remarks 49References 53Appendix A: Scatter plots for the K-means clustering for Type No. 3 suspicious customers 58Appendix B: Scatter plots for the SVM clustering for Type No. 3 suspicious customers 66Appendix C: Scatter plots for the K-means clustering for Type No. 6 suspicious customers 74Appendix D: Scatter plots for the SVM clustering for Type No. 6 suspicious customers 76 zh_TW dc.format.extent 4058942 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107258006 en_US dc.subject (關鍵詞) 洗錢防制 zh_TW dc.subject (關鍵詞) K-means分群演算法 zh_TW dc.subject (關鍵詞) 支援向量機 zh_TW dc.subject (關鍵詞) 異常檢測 zh_TW dc.subject (關鍵詞) 疑似洗錢交易態樣 zh_TW dc.subject (關鍵詞) 證券業 zh_TW dc.subject (關鍵詞) Anti-money laundering en_US dc.subject (關鍵詞) K-means en_US dc.subject (關鍵詞) Support vector machine en_US dc.subject (關鍵詞) Anomaly detection en_US dc.subject (關鍵詞) Suspicious types en_US dc.subject (關鍵詞) Securities industry en_US dc.title (題名) 機器學習在證券業反洗錢監控之應用 zh_TW dc.title (題名) Applying Machine Learning on Anti-Money Laundering Detection in Securities Firms en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1.Anti-Money Laundering Division (AMLD) (2017). Anti-Money Laundering Annual Report, 2017.2.Anti-Money Laundering Division (AMLD) (2018). Anti-Money Laundering Annual Report, 2018.3.Anti-Money Laundering Division (AMLD) (2019). Anti-Money Laundering Annual Report, 2019.4.Anti-Money Laundering Office, Executive Yuan (2018, May). National Money Laundering and Terrorist Financing Risk Assessment Report.5.Asia/Pacific Group on Money Laundering (2019). Mutual Evaluation Report of Chinese Taipei.6.Ben-Gal, I. (2005). Outlier detection. In Data mining and knowledge discovery handbook (pp. 131-146). Springer, Boston, MA.7.Bolton, R. J., and Hand, D. J. (2002). Statistical fraud detection: A review. Statistical science, 17(3), 235-255.8.Boser, B. E., Guyon, I. M., and Vapnik, V. N. (1992, July). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory (pp. 144-152).9.Breslow, S., Hagstroem, M., Mikkelsen, D., and Robu, K. (2017). The new frontier in anti–money laundering. McKinsey and Company, November.10.Chen, Z., Teoh, E. N., Nazir, A., Karuppiah, E. K., and Lam, K. S. (2018). Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection: a review. Knowledge and Information Systems, 57(2), 245-285.11.Cortes, C., and Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.12.Dreżewski, R., Sepielak, J., and Filipkowski, W. (2015). The application of social network analysis algorithms in a system supporting money laundering detection. Information Sciences, 295, 18-32.13.European Commission (2021). Proposal for a Regulation establishing the Authority for Anti-Money Laundering and Countering the Financing of Terrorism and amending Regulations (EU) No 1093/2010, (EU) 1094/2010, (EU) 1095/2010.14.Fenergo officials (2018). Firms Fined $26B Over the Past Decade: Fenergo.15.Financial Action Task Force on Money Laundering (FATF) (2009). Money Laundering and Terrorist Financing in the Securities Sector.16.Financial Action Task Force on Money Laundering (FATF) (2012). FATF Recommendations 2012.17.Financial Examination Bureau, FSC (2017). Template for Guidelines Governing Anti-Money Laundering and Countering Terrorism Financing of Securities Firms.18.Financial Supervisory Commission (2017). Regulations Governing Anti-Money Laundering of Financial Institutions.19.Gao, Z., and Ye, M. (2007). A framework for data mining-based anti-money laundering research. Journal of Money Laundering Control, 10(2), 170-179.20.Garcia, E., Regan, P., Stern, J., Johnson, W., Macallister, R., Reidenberg, J., ... and Welling, S. (1995). Information Technologies for the Control of Money Laundering. OTA-ITC-630, Washington, DC.21.Hartigan, J. A. (1975). Clustering algorithms. John Wiley and Sons, Inc..22.Hartigan, J. A., and Wong, M. A. (1979). AK‐means clustering algorithm. Journal of the Royal Statistical Society: Series C (Applied Statistics), 28(1), 100-108.23.Hsu, C. W., Chang, C. C., and Lin, C. J. (2003). A practical guide to support vector classification.24.Hubert, M., and Vandervieren, E. (2008). An adjusted boxplot for skewed distributions. Computational statistics and data analysis, 52(12), 5186-5201.25.Keerthi, S. S., and Lin, C. J. (2003). Asymptotic behaviors of support vector machines with Gaussian kernel. Neural computation, 15(7), 1667-1689.26.Keyan, L., and Tingting, Y. (2011, November). An improved support-vector network model for anti-money laundering. In 2011 Fifth International Conference on Management of e-Commerce and e-Government (pp. 193-196). IEEE.27.Kingdon, J. (2004). AI fights money laundering. IEEE Intelligent Systems, 19(3), 87-89.28.Kirkland, J. D., Senator, T. E., Hayden, J. J., Dybala, T., Goldberg, H. G., and Shyr, P. (1999). The nasd regulation advanced-detection system (ads). AI Magazine, 20(1), 55-55.29.Le Khac, N. A., and Kechadi, M. T. (2010, December). Application of data mining for anti-money laundering detection: A case study. In 2010 IEEE International Conference on Data Mining Workshops (pp. 577-584). IEEE.30.Le-Khac, N. A., Markos, S., and Kechadi, M. T. (2009, September). Towards a new data mining-based approach for anti-money laundering in an international investment bank. In International Conference on Digital Forensics and Cyber Crime (pp. 77-84). Springer, Berlin, Heidelberg.31.LexisNexis (2020). Global True Cost of Compliance 2020 report.32.LexisNexis Risk Solutions (2018). 2018 True Cost of AML Compliance report for the United States.33.Lin, H. T., and Lin, C. J. (2003). A study on sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods. submitted to Neural Computation, 3(1-32), 16.34.Liu, R., Qian, X. L., Mao, S., and Zhu, S. Z. (2011, May). Research on anti-money laundering based on core decision tree algorithm. In 2011 Chinese Control and Decision Conference (CCDC) (pp. 4322-4325). IEEE.35.Liu, X., Zhang, P., and Zeng, D. (2008, June). Sequence matching for suspicious activity detection in anti-money laundering. In International conference on intelligence and security informatics (pp. 50-61). Springer, Berlin, Heidelberg.36.Mylevaganam, S. (2017). The Analysis of Human Development Index (HDI) for Categorizing the Member States of the United Nations (UN). Open Journal of Applied Sciences, 7(12), 661-690.37.Noble, J. C. (2021). 7. Money Laundering. In White-Collar and Financial Crimes (pp. 91-104). University of California Press.38.Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.39.Romaniuk, P., Haber, J., and Murray, G. (2007). Suspicious activity reporting. The CPA Journal, 77(3), 70.40.Senator, T. E., Goldberg, H. G., Wooton, J., Cottini, M. A., Khan, A. U., Klinger, C. D., ... and Wong, R. W. (1995). Financial crimes enforcement network AI system (FAIS) identifying potential money laundering from reports of large cash transactions. AI magazine, 16(4), 21-21.41.Syarif, I., Prugel-Bennett, A., and Wills, G. (2016). SVM parameter optimization using grid search and genetic algorithm to improve classification performance. Telkomnika, 14(4), 1502.42.Tan, P. N., Steinbach, M., and Kumar, V. (2016). Introduction to data mining. Pearson Education India.43.Tang, J., and Yin, J. (2005, August). Developing an intelligent data discriminating system of anti-money laundering based on SVM. In 2005 International conference on machine learning and cybernetics (Vol. 6, pp. 3453-3457). IEEE.44.Thorndike, R. L. (1953). Who belongs in the family?. Psychometrika, 18(4), 267-276.45.Umadevi, P., and Divya, E. (2012, December). Money laundering detection using TFA system. In International Conference on Software Engineering and Mobile Application Modelling and Development (ICSEMA 2012) (pp. 1-8). IET.46.United States Department of the Treasury (2015). National Money Laundering Risk Assessment.47.Wang, S. N., and Yang, J. G. (2007, August). A money laundering risk evaluation method based on decision tree. In 2007 international conference on machine learning and cybernetics (Vol. 1, pp. 283-286). IEEE.48.Watkins, R. C., Reynolds, K. M., Demara, R., Georgiopoulos, M., Gonzalez, A., and Eaglin, R. (2003). Tracking dirty proceeds: exploring data mining technologies as tools to investigate money laundering. Police Practice and Research, 4(2), 163-178.49.Zhang, Y., and Trubey, P. (2019). Machine learning and sampling scheme: An empirical study of money laundering detection. Computational Economics, 54(3), 1043-1063.50.Zhang, Z., Salerno, J. J., and Yu, P. S. (2003, August). Applying data mining in investigating money laundering crimes. In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining (pp. 747-752). zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200104 en_US
