The aim of this study attempts to introduce how a credit scoring model can be used to help finance/leasing companies manage and reinforce their auto loan approval process. Credit scoring models are most frequently applied methods adopted by banks when evaluating loan applications. This is a data-driven approach and it is built by using historical data and statistical techniques to identify the possibility that the failure by borrowers to make repayments in accordance with the term of a loan. Finance/leasing companies focus on the lending business in high risk borrowers. Default risk is what finance/leasing companies have to be concerned about.
In this study, a real data of auto loan product was used to build a credit scoring model. The logistic regression is the most common method to establish the model and the model validation was also conducted to prove the effectiveness. The paper presents a credit scoring model that provides finance/leasing companies an objective way to measure and manage the credit risk. The model has also identified the risk factors associated with measuring the credit risk. This thesis illustrated how the credit scoring model works and it is recommended financing/leasing companies should develop their own credit scoring model.

1. Introduction 1
1.1. The Business Growth of Auto Loan in Finance/Leasing Companies 1
1.2. Research Motivation 2
1.3. Research Objectives 6
1.4. Research Structure 6
2. Literature Review 8
2.1. How the Banks Reduce the Credit Risk 8
2.2. The Statistical Technique to Establish a Credit Rating System 9
3. A Case of Leasing Company 10
3.1. Market Segmentation 10
3.2. Common Practice of Running Auto Loan Business and the Difficulties 11
3.3. Company SWOT Analysis 13
4. Research Methodology 17
4.1. Model Design 17
4.2. Model Development Process 18
4.2.1. Data Preparation 18
4.2.2. Data Analysis 19
4.2.3. Model Development 23
4.2.4. Model Validation 35
5. Implementation and Use 41
5.1. The Proposed Framework 41
5.2. Cost-Benefit Analysis 42
6. Research Conclusion 44
References 46
Appendix 49

1. Crook, J.N., Edelman, D.B., Thomas, L.C. (2002). Credit Scoring and its Applications. Philadelphia: Siam
2. Finlay, S. (2012). Credit Scoring, Response Modeling, and Insurance Rating: A Practical Guide to Forecasting Consumer Behavior (2nd edition). Hampshire UK: Palgrave Macmillan
3. Guo, J.J., Meng, J.W., Shan, L., Wang, H.S. (2010).12 Lessons for Credit Rating Models. Taiwan: Taiwan Academy of Banking and Finance
4. Hosmer Jr., D.W., Lemeshow, S., Sturdivant, R.X. (2013). Applied Logistic Regression (3rd edition). New Jersey:John Wiley & Sons, Inc.
5. Mays, E. (2001). Handbook of Credit Scoring. Chicago: Glenlake Publishing Company
6. Olson, D.L., Wu, D.D. (2008). Enterprise Risk Management. Canada: World Scientific Publishing Co. Pte. Ltd
7. Shu, X. (2020). Knowledge Discovery in the Social Science: a Data Mining Approach. Oakland California: University of California
8. Siddiqi, N. (2006). Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring. Hoboken, New Jersy: John Wiley & Sons, Inc.
9. Bank for International Settlements (2005), Working Paper No. 14 Studies on the Validation of Internal Rating Systems. Retrieved from: https://www.bis.org/publ/bcbs_wp14.pdf (access March 15th, 2020)
10. Bank for International Settlements (2017), Basel III: Finalising post-crisis reforms. Retrieved from: https://www.bis.org/bcbs/publ/d424.htm (access March 7th, 2020)
11. Chen, G.H., Chu, M.J., Huang, J.C. (2011). A research on credit rating model of leasing industry. (Master’s thesis, Ming Chuan University, Taipei, Taiwan) Retrieved from: http://oplab.im.ntu.edu.tw/csimweb/system/application/views/files/ICIM/20110082
12. Financial Supervisory Commission, R.O.C. Taiwan (2020). How to enhance the function of Consumer Debt Relief Program and the Regulation Governing for the Improvement of Banking Business of Credit Card and Cash Card. Retrieved from: https://law.fsc.gov.tw/law/LawContent.aspx?id=FE057275&KeyWord=%e6%b6%88%e8%b2%bb%e9%87%91%e8%9e%8d%e5%82%b5%e5%8b%99%e5%8d%94%e5%95%86%e6%a9%9f%e5%88%b6 (accessed June 16th, 2020)
13. Banking Bureau (2020). Banking Statistics. Retrieved from: https://www.banking.gov.tw/ch/home.jsp?id=595&parentpath=0,590 (accessed June 10th, 2020)
14. Chailease Holding (2019). Annual Report 2018-2019。Retrieved from: http://www.chaileaseholding.com/ImgChaileaseHolding/20200519183251.pdf , (accessed April 10th, 2020)
15. Ding, J.J. (2004).Study of Consumer Credit Risk - Introduction to Credit Scoring. Retrieved from: https://member.jcic.org.tw/main_member/fileRename.aspx?fid=298&kid=1 (accessed June 10th, 2020)
16. Lai, B.Z. (2006). The Current Development Status of Consumer Credit Scoring System. Retrieved from: https://member.jcic.org.tw/main_member/fileRename.aspx?fid=378&kid=1 (accessed June 10th, 2020)
17. Lai, B.Z., Tsai, R.M. (August, 2009). Consumer Credit Scoring System Product (J10) the Use in the Approval Process of Credit Card. Retrieved from: https://www.google.com/url?client=internal-element-cse&cx=010192925252739662080:8bojmtikgsc&q=https://www.jcic.org.tw/main_ch/fileRename/fileRename.aspx%3Ffid%3D631%26kid%3D1&sa=U&ved=2ahUKEwjO-J7F2_boAhUpxYsBHX_1CJI4FBAWMAV6BAgFEAI&usg=AOvVaw33ZTMH_-AyymIcZrTQJwDr (accessed March 20th, 2020)
18. Liu, M.H., Wu, C.L. (July 24th, 2015). Reach an agreement of giving the permission to the financing and leasing companies of non-JCIC members to apply for credit reports on behalf of consumers. Retrieved from: https://www.ndc.gov.tw/News_Content.aspx?n=114AAE178CD95D4C&sms=DF717169EA26F1A3&s=15214408D3578A59 (accessed December 10th, 2019)