DocumentCode
2286660
Title
Incremental learning algorithm of least squares support vector machines based on Renyi entropy
Author
Zhao Guan-hua ; Hao Min
Author_Institution
Sch. of Manage., Tianjin Univ., Tianjin, China
fYear
2009
fDate
14-16 Sept. 2009
Firstpage
95
Lastpage
100
Abstract
This paper introduces Renyi entropy and incremental learning algorithm into the financial distress prediction of enterprises and advances an incremental learning algorithm on least squares support vector machine based on Renyi entropy. By analysis and comparison of LS-SVM incremental learning algorithm based on Renyi entropy,traditional LS-SVM algorithm and standard SVM algorithm,LS-SVM incremental learning algorithm based on the Renyi entropy are evidently superior to the traditional LS-SVM algorithm and the standard SVM in terms of the number of training samples and computing time. This confirms the effectiveness and superiority of the introduction of Renyi entropy into the field of financial distress prediction.
Keywords
entropy; finance; learning (artificial intelligence); least squares approximations; support vector machines; LS-SVM method; Renyi entropy; enterprises financial distress prediction; incremental learning algorithm; least squares support vector machine; Algorithm design and analysis; Conference management; Entropy; Financial management; Forward contracts; Least squares methods; Machine learning; Machine learning algorithms; Quadratic programming; Support vector machines; LS-SVM; Renyi entropy; factor analysis; financial distress prediction; incremental learning algorithm; standard SVM;
fLanguage
English
Publisher
ieee
Conference_Titel
Management Science and Engineering, 2009. ICMSE 2009. International Conference on
Conference_Location
Moscow
Print_ISBN
978-1-4244-3970-6
Electronic_ISBN
978-1-4244-3971-3
Type
conf
DOI
10.1109/ICMSE.2009.5317570
Filename
5317570
Link To Document