I am very pleased to attend the International Seminar on the Application of Credit Information Products in Managing Credit Risks of Commercial Banks. First, on behalf of the People’s Bank of China, I would like to express gratitude to our co-sponsor of this seminar, the International Finance Corporation. Also, I would like to extend warmest welcome and gratitude to experts from abroad countries...

Even for the most experienced Chief Technology Officer (CTO) or Chief Risk Officer (CRO), the decision to invest in a credit origination system can seem daunting. While there is no shortage of research available on this subject from a retail credit standpoint, in the domain of commercial and corporate lending the treasure chest of useful hints and tips to guide the prospective purchaser is far ...

Evaluation of credit risk is an important task before loan of a project. However, effective methods have not developed until Support Vector Machine is brought. In this paper, because SVM is a kind of general forward-feedback network, it is applied to how to evaluate credit risk of commercial loan in banks. Empirical results show that SVM is effective and more advantageous than BP neural network...

We apply machine-learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk. By combining customer transactions and credit bureau data from January 2005 to April 2009 for a sample of a major commercial bank’s customers, we are able to construct out-of-sample forecasts that significantly improve the classification rates of credit-card-holder delinquencies...

Neural nets have become one of the most important tools using in credit scoring. Credit scoring is regarded as a core appraised tool of commercial banks during the last few decades. The purpose of this paper is to investigate the ability of neural nets, such as probabilistic neural nets and multi-layer feed-forward nets, and conventional techniques such as, discriminant analysis, probit analysi...

With the help of a commercial bank in China, we studied consumer credit card debt behavior in correlation with demographics, attitude, personality, and credit card features factors. The study was conducted by using mail-in questionnaires, which were sent to credit card holders who was using or had used either revolving credit or petty installment plans. According to regression functions, we fou...