Title: Research on probability of default prediction based on loan company's credit fund trading behaviours

Authors: Bo Hong; Xingsheng Xie; Haoming Guo

Addresses: School of Management, Hefei University of Technology, Hefei 230009, China ' Automation Department, University of Science and Technology of China, Hefei 230027, China ' Automation Department, University of Science and Technology of China, Hefei 230027, China

Abstract: The probability of default (PD) is an important parameter to quantify credit risk, which is usually impacted by some less frequent accidents, such as market factors or the macroeconomic climate changes. The traditional approaches to estimate PD, such as expert-method or pattern classification based on a set of financial indicators, are heavily dependent on financial reports offered by borrow-customers, and can lead to unreliability and long-time lags in forecast. According to the business schema of loan-fund expenditure surveillance in some commercial banks in China, this paper proposes a support vector machine (SVM) PD classifier constructed on a set of loan-fund expenditure behaviour features, which can be directly collected from the fund trading databases of the banks in time. For the sake of comparison, both of the Logistic and SVM models are tested in this paper to predict PD, and their classification accuracy can be up to 84.6% and 89.4% respectively.

Keywords: credit risk; default probability; pattern classification; loan fund expenditure behaviour; credit fund trading; trading behaviour; China; banking industry; support vector machines; SVM; commercial banks.

DOI: 10.1504/IJSPM.2014.066368

International Journal of Simulation and Process Modelling, 2014 Vol.9 No.4, pp.240 - 245

Received: 17 Jan 2014
Accepted: 16 May 2014
Published online: 30 Apr 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article