A Study of the Default Factors on the Student Loan

• Main Authors: Chung-Tsai Chang, 張忠財
• Other Authors: Jian-Hsin Chou
• Format: Others
• Language: zh-TW
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/29190985568528510349

碩士 === 國立高雄第一科技大學 === 財務管理所 === 95 === Abstract Recently, the increasing default rates of student loans have been a critical issue for bank management. However, comparatively little attention has been paid to the key practical problem of investigating the determining factors affecting the default rates in the academics. In this paper, we use the Logistic Regression method to explore the main factors of nonperforming student loans. Meanwhile, we select the samples that the student-loans debtors begin to repay their debts until the end of March, 2007. There are total 1061 samples which are selected from one domestic bank. In addition, the normal accounts are 502, and the overdue accounts are 559. The empirical results indicate that there exists a negative relationship between the default rate and three variables, including times for application, kinds of school, and public/ private school under 5% significant level. However, it shows a positive relationship between the default rate and the female/male attribute. In addition, the accuracy of our credit evaluation model reaches 89.4% of which non-breaching parties has 95.0% accuracy rate, breaching parties has 84.4% accuracy rate.