Attribute-value specification in customs fraud detection: a human-aided approach

ABSTRACT

With the growing importance of foreign commerce comes also greater opportunities for fraudulent behaviour. As such, governments must try to detect frauds as soon as they take place, if they are to avoid the profound damage to the society frauds may cause. Although current fraud detection systems can be used on this endeavour with reasonable accuracy, they still suffer with the inconsistencies and ambiguities of unstructured databases, especially in customs. To deal with this kind of problem, we propose a twofold approach: building a brand new structured database, keeping it as clean as possible; and mining the current database for the desired information. Then, as a first contribution, we present a methodology for mining product attribute-value pairs in unstructured text datasets, bringing more structure to the current customs database. Next, as our second contribution, we introduce a system for building a structured database for the Brazilian customs and keeping it with as few redundancies as possible. Both systems aim at building datasets capable of improving the accuracy of fraud detection systems.

REFERENCES

• 1: Sonia Bergamaschi , Francesco Guerra , Maurizio Vincini, A Data Integration Framework for e-Commerce Product Classification, Proceedings of the First International Semantic Web Conference on The Semantic Web, p.379-393, June 09-12, 2002
• 2: R. J. Bolton and D. J. Hand. Statistical fraud detection: A review. Statistical Science, 17(3):235--255, 2002.
• 3: Vinayak Borkar , Kaustubh Deshmukh , Sunita Sarawagi, Automatic segmentation of text into structured records, ACM SIGMOD Record, v.30 n.2, p.175-186, June 2001
• 4: E. W. Bowen. Roman commerce in the early empire. The Classical Weekly, 21(26):201--206, May 14 1928.
• 5: Luciano A. Digiampietri , Norton Trevisan Roman , Luis A. A. Meira , Jorge Jambeiro Filho , Cristiano D. Ferreira , Andreia A. Kondo , Everton R. Constantino , Rodrigo C. Rezende , Bruno C. Brandao , Helder S. Ribeiro , Pietro K. Carolino , Antonella Lanna , Jacques Wainer , Siome Goldenstein, Uses of artificial intelligence in the Brazilian customs fraud detection system, Proceedings of the 2008 international conference on Digital government research, May 18-21, 2008, Montreal, Canada
• 6: A. Doig and S. Riley. Corruption and Integrity Improvement Initiatives in Developing Countries, chapter Corruption and Anti-Corruption Strategies: Issues and Case Studies from Developing Countries. UNDP, New York, 1998.
• 7: K. M. Dye. Performance Accountability and Combating Corruption, chapter Corruption and Fraud Detection by Supreme Audit Institutions, pages 299--317. The World Bank, Washington, D.C., 2007.
• 8: Rayid Ghani , Katharina Probst , Yan Liu , Marko Krema , Andrew Fano, Text mining for product attribute extraction, ACM SIGKDD Explorations Newsletter, v.8 n.1, p.41-48, June 2006 [doi>10.1145/1147234.1147241]
• 9: Erik Hatcher , Otis Gospodnetic, Lucene in Action (In Action series), Manning Publications Co., Greenwich, CT, 2004
• 10: Victoria Hodge , Jim Austin, A Survey of Outlier Detection Methodologies, Artificial Intelligence Review, v.22 n.2, p.85-126, October 2004 [doi>10.1023/B:AIRE.0000045502.10941.a9]
• 11: M. Jans, N. Lybaert, and K. Vanhoof. Data mining for fraud detection: Toward an improvement on internal control systems? In Proceedings of the 30th Annual Congress European Accounting Association (EAA2007)., Lisbon, Portugal, 2007.
• 12: Efstathios Kirkos , Charalambos Spathis , Yannis Manolopoulos, Data Mining techniques for the detection of fraudulent financial statements, Expert Systems with Applications: An International Journal, v.32 n.4, p.995-1003, May, 2007 [doi>10.1016/j.eswa.2006.02.016]
• 13: S. Maes, K. Tuyls, B. Vanschoenwinkel, and B. Manderick. Credit card fraud detection using bayesian and neural networks. In Proceedings of the 1st International NAISO Congress on Neuro Fuzzy Technologies, Havana, Cuba, 2002.
• 14: N. T. Roman, E. R. Constantino, H. Ribeiro, J. J. Filho, A. Lanna, S. K. Goldenstein, and J. Wainer. Carancho -- a decision support system for customs. In Proceedings of ECML PKDD 2006 Workshop on Practical Data Mining: Applications, Experiences and Challenges, pages 100--103, Berlin, Germany, September 22nd 2006.
• 15: H. Shao, H. Zhao, and G.-R. Chang. Applying data mining to detect fraud behavior in customs declaration. In Proceedings of the First International Conference on Machine Learning and Cybernetics, volume 3, pages 1241--1244, Beijing, China, November, 4--5 2002.
• 16: A. K. Singh, R. Sahu, and K. Ujjwal. Decision support system in customs assessment to detect valuation frauds. In Proceedings of the 2003 IEEE International Engineering Management Conference (IEMC-2003): Managing Technologically Driven Organizations: The Human Side of Innovation and Change, pages 546--550, Albany, USA, November, 2--4 2003. IEEE.
• 17: U.S. Department of State. International Narcotics Control Strategy Report. Volume II: Money Laundering and Financial Crimes, 2005.
• 18: Kenji Yamanishi , Jun-Ichi Takeuchi , Graham Williams , Peter Milne, On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms, Data Mining and Knowledge Discovery, v.8 n.3, p.275-300, May 2004 [doi>10.1023/B:DAMI.0000023676.72185.7c]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS

Additional Classification:
  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING