DocumentCode
3458473
Title
Risk Management of Residential Mortgage in China Using Date Mining A Case Study
Author
Gan, Qiwei ; Luo, Binjie ; Lin, Zhangxi
Author_Institution
Lab. of Financial Intell. & Financial Eng., Southwestern Univ. of Finance & Econ., Chengdu, China
fYear
2009
fDate
June 30 2009-July 2 2009
Firstpage
1378
Lastpage
1383
Abstract
This paper investigates the risk management for residential mortgage in China. The paper finds out that the Chinese commercial banks have to take all the risks of residential mortgages. By examining a causal model of Chinapsilas mortgage market, the paper reveals that with relatively tight financial regulations by Chinese central bank, commercial banks have to solely depend on the credit system to screen out potential default loan applicants. Therefore, it is urgent for commercial banks to build an effective screening system to reduce the risk introduced by loan defaults. The paper reports an analytic study based on a real dataset of 641,988 observations provided by a Chinese commercial bank. The outcomes suggest that the classification model is effective for credit scoring with the data collected at China, and, however, the quality of the data needs to be improved for more precise default risk management.
Keywords
data mining; mortgage processing; real estate data processing; risk management; China; Chinese central bank; Chinese commercial banks; credit scoring; credit system; data mining; financial regulations; loan applicants; loan defaults; residential mortgage; risk management; Business; Cities and towns; Data mining; Finance; Gallium nitride; History; Instruments; Loans and mortgages; Risk analysis; Risk management; China; Credit scoring; data mining; default risk management; residential mortgage loan;
fLanguage
English
Publisher
ieee
Conference_Titel
New Trends in Information and Service Science, 2009. NISS '09. International Conference on
Conference_Location
Beijing
Print_ISBN
978-0-7695-3687-3
Type
conf
DOI
10.1109/NISS.2009.253
Filename
5260598
Link To Document