TY - JOUR
T1 - Credit rating analysis with support vector machines and neural networks
T2 - A market comparative study
AU - Huang, Zan
AU - Chen, Hsinchun
AU - Hsu, Chia Jung
AU - Chen, Wun Hwa
AU - Wu, Soushan
N1 - Funding Information:
Hsinchun Chen is McClelland Professor of MIS and Andersen Professor of MIS at the University of Arizona, where he is the director of the Artificial Intelligence Lab and the director of the Hoffman E-Commerce Lab. His articles have appeared in Communications of the ACM, IEEE Computer, Journal of the American Society for Information Science and Technology, IEEE Expert, and many other publications. Professor Chen has received grant awards from the NSF, DARPA, NASA, NIH, NIJ, NLM, NCSA, HP, SAP, 3COM, and AT and T. He serves on the editorial board of Decision Support Systems and the Journal of the American Society for Information Science and Technology, and has served as the conference general chair of the International Conferences on Asian Digital Library in the past 4 years.
Funding Information:
This research is partly supported by NSF Digital Library Initiative-2, “High-performance Digital Library Systems: From Information Retrieval to Knowledge Management”, IIS-9817473, April 1999–March 2002.
PY - 2004/9
Y1 - 2004/9
N2 - Corporate credit rating analysis has attracted lots of research interests in the literature. Recent studies have shown that Artificial Intelligence (AI) methods achieved better performance than traditional statistical methods. This article introduces a relatively new machine learning technique, support vector machines (SVM), to the problem in attempt to provide a model with better explanatory power. We used backpropagation neural network (BNN) as a benchmark and obtained prediction accuracy around 80% for both BNN and SVM methods for the United States and Taiwan markets. However, only slight improvement of SVM was observed. Another direction of the research is to improve the interpretability of the AI-based models. We applied recent research results in neural network model interpretation and obtained relative importance of the input financial variables from the neural network models. Based on these results, we conducted a market comparative analysis on the differences of determining factors in the United States and Taiwan markets.
AB - Corporate credit rating analysis has attracted lots of research interests in the literature. Recent studies have shown that Artificial Intelligence (AI) methods achieved better performance than traditional statistical methods. This article introduces a relatively new machine learning technique, support vector machines (SVM), to the problem in attempt to provide a model with better explanatory power. We used backpropagation neural network (BNN) as a benchmark and obtained prediction accuracy around 80% for both BNN and SVM methods for the United States and Taiwan markets. However, only slight improvement of SVM was observed. Another direction of the research is to improve the interpretability of the AI-based models. We applied recent research results in neural network model interpretation and obtained relative importance of the input financial variables from the neural network models. Based on these results, we conducted a market comparative analysis on the differences of determining factors in the United States and Taiwan markets.
KW - Backpropagation neural networks
KW - Bond rating prediction
KW - Credit rating analysis
KW - Cross-market analysis
KW - Data mining
KW - Input variable contribution analysis
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=2442665617&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=2442665617&partnerID=8YFLogxK
U2 - 10.1016/S0167-9236(03)00086-1
DO - 10.1016/S0167-9236(03)00086-1
M3 - Article
AN - SCOPUS:2442665617
VL - 37
SP - 543
EP - 558
JO - Decision Support Systems
JF - Decision Support Systems
SN - 0167-9236
IS - 4
ER -