DocumentCode :
571328
Title :
Personal Credit Assessment Based on KPCA and SVM
Author :
Wang, Jing ; Zhou, Yongsheng ; Du, Xinjian ; He, Mingke
Author_Institution :
Sch. of Bus., Beijing Technol. & Bus. Univ., Beijing, China
fYear :
2012
fDate :
18-21 Aug. 2012
Firstpage :
25
Lastpage :
28
Abstract :
Personal credit assessment is carried out by setting up a mathematical model to count, calculate and analyze the personal credit data. At present personal credit assessment has already became a kind of worldwide industry. In this paper we combine kernel principal component analysis and support vector machine to propose a new mathematical model based on KPCA and SVM. We extract personal credit data using KPCA, then use them to train SVM. Experiments show that the new method put forward in this paper is superior to other methods in assessing precision and assessing efficiency.
Keywords :
data analysis; mathematical analysis; principal component analysis; socio-economic effects; support vector machines; KPCA; SVM training; kernel principal component analysis; mathematical model; personal credit assessment; personal credit data analysis; support vector machine; worldwide industry; Business; Eigenvalues and eigenfunctions; Feature extraction; Kernel; Principal component analysis; Support vector machines; Training; Kernel Principal Component Analysis; Kernel function; Support Vector Machine;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Business Intelligence and Financial Engineering (BIFE), 2012 Fifth International Conference on
Conference_Location :
Lanzhou
Print_ISBN :
978-1-4673-2092-4
Type :
conf
DOI :
10.1109/BIFE.2012.13
Filename :
6305072
Link To Document :
بازگشت