HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE
Department of Computer Science Seminar
A Hybrid Credit Scoring Model Based on Genetic Programming and Support Vector Machine
Dr. Zhang Defu
Department of Computer Science
Date: August 25, 2009 (Tuesday)
Time: 2:30 - 3:30 pm
Venue: RRS905, Sir Run Run Shaw Building, Ho Sin Hang Campus
Credit scoring has obtained more and more attention as the credit industry can benefit from reducing potential risks. Hence, many different useful techniques, known as the credit scoring models, have been developed by banks and researchers in order to solve the problems involved during the evaluation process. In this paper, a hybrid credit scoring model (HCSM) is developed to deal with the credit scoring problem by incorporating the advantages of genetic programming and support vector machines. Two credit data sets in UCI database are selected as the experimental data to demonstrate the classification accuracy of the HCSM. Compared with Support Vector Machines, Genetic Programming, Decision Tree Classifiers, Logistic Regression, and Back-propagation Neural Network, HCSM can obtain better classification accuracy.
Dr. Zhang Defu received his bachelor degree in computational mathematics in 1996, and master degree in computational mathematics in 1999, both from Xiangtan University, and his Ph.D. degree in computer software and its theory from Huazhong University of Science & Technology. He was a senior researcher of Shanghai Jinxin financial engineering academe from Jun. 2002 to Apr. 2003. He worked as a PostDoc at the Longtop for financial data mining group from 2006 to 2008. From Jun. 2008 to Sept. 2008, and from July. 2009 to Sept. 2009, he worked as a research fellow of Hong Kong City University. Now he works in the department of Computer Science at Xiamen University.
His research interests include all aspects of computational intelligence, finance data mining and game search. He works mainly in the intelligent solving of NP-hard problems, such as Packing, Scheduling, timetabling, SAT etc, and makes use of modern artificial intelligence techniques, for example, neural network, genetic programming, support vector machine to develop stock forecasting systems and credit scoring systems. He does research on game search algorithms for newly invented games and Chinese classical games.
Current projects include China 985 information technology fund (Grant No. 0000-X07204), the National Natural Science Foundation of China (Grant no. 60773126) and the Province Natural Science Foundation of Fujian (Grant no. A0710023). He has developed a packing software (include 2- dimensional and 3-dimensional packing), credit scoring system and stock forecasting software. He currently has a research group consisted of nine graduate students, these students are very excellent and some students took part in ACM/ICPC contest. The homepage of research group is http://188.8.131.52/
********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
Department of Computer Science, Hong Kong Baptist University