Impacting Factors of Default Risk of Personal Housing Loans in China: Based on MCLP Model

Li Zhao; Guangrui He

doi:10.62051/ijgem.v5n1.01

Authors

Li Zhao
Guangrui He

DOI:

https://doi.org/10.62051/ijgem.v5n1.01

Keywords:

Personal housing loans, Loan default risk, MCLP model

Abstract

A large-scale default on personal housing loans will have a significant negative impact on the stability of the financial system and the smooth operation of the macro-economy. After the pandemic, preventing personal housing loan risks has become particularly important. Based on personal housing loans from commercial banks in China, a personal housing loan default risk model was constructed using the MCLP model, and the prediction results of the MCLP model were compared with those of the traditional logistic model to identify indicators that may affect default risk of personal housing loans. It was found that the MCLP had higher accuracy than the traditional logistic model. Empirical findings indicated that the education level, employment status, monthly household income, and census register of housing loan borrowers were primary factors influencing customer defaults.

Downloads

Download data is not yet available.

References

[1] Berry M, Dalton T. Home ownership into the new millennium: a view from the margin [J]. Urban Policy and Research, 2000, 18(4):435-454.

[2] Xu Yanyan, Zhao Zhenglong Empirical analysis and countermeasures research on the pro cyclical credit risk of commercial banks in China [J] New Finance, 2011 (2): 40-44.

[3] Klein B, Leffler K B. The role of market forces in assuring contractual performance [J]. The he Journal of Political Economy, 1981, 89(4):615-641.

[4] Myers J H, Forgy E W. The development of numerical credit evaluation systems [J]. Journal of the American Statistical Association, 1936, 303 (58):799-806.

[5] Glover F, Laguna M. Tabu search [M]. US: Springer US, 1999.

[6] Li A, Yu Y, Liu Z. Sensitivity Analysis of b in MCLP model for credit card-holders classification [J]. Procedia Computer Science, 2013, 17 (1):1023-1031.

[7] Shi Y, Wise M, Luo M, etal. Data mining in credit card portfolio management: a multiple criteria decision making approach [M]. US: Springer Berlin Heidelberg, 2001.

[8] Kou G, Liu X, Peng Y, etal. Multiple criteria linear programming approach to data mining: models, algorithm designs and software development [J]. Optimization Methods and Software, 2003, 18(4):453-473.

[9] Li A, Shi Y, He J. MCLP based methods for improving “bad” catching rate in credit cardholder behavior analysis [J]. Applied Soft Computing, 2008, 8(2):1259-1265.

[10] Jia Shenghua, Li, Hang. Noise traders' expectations and real estate foam: an empirical study —based on 35 large and medium-sized cities [J] Audit and Economic Research, 2014 (3): 85-92

[11] Li A, Yu Y, Liu Z. Sensitivity Analysis of b in MCLP model for credit card-holders classification [J]. Procedia Computer Science, 2013, 17 (1):1023-1031.