Skip to main navigation Skip to search Skip to main content

Application of support vector machines in paying rate forecasting

  • Chong Wu*
  • , Pu Chen
  • *Corresponding author for this work
  • School of Management, Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper deals with the application of a novel neural network technique, support vector machine (SVM), in financial time series forecasting. This study applies SVM to predict the paying rate index. The objective of this paper is to examine the feasibility of SVM in paying rate forecasting by comparing it with a feed-forward backpropagation (BP) neural network. We choose Gaussian function as its Kernel function.The experiment shows that SVM outperforms the feed-forward BP neural network based on the criteria of mean absolute error(MAE), mean absolute percent error(MAPE), mean squared error(MSE)and root mean square error(RMSE). Analysis of the experimental results proved that it is advantageous to apply SVMs to forecast paying rate.

Original languageEnglish
Title of host publicationProceedings of 2006 International Conference on Management Science and Engineering, ICMSE'06 (13th)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1494-1497
Number of pages4
ISBN (Print)7560323553, 9787560323558
DOIs
StatePublished - 2006
Externally publishedYes
Event2006 International Conference on Management Science and Engineering, ICMSE'06 - Lille, France
Duration: 5 Oct 20067 Oct 2006

Publication series

NameProceedings of 2006 International Conference on Management Science and Engineering, ICMSE'06 (13th)

Conference

Conference2006 International Conference on Management Science and Engineering, ICMSE'06
Country/TerritoryFrance
CityLille
Period5/10/067/10/06

Keywords

  • BP neural network
  • Financial time series
  • Forecasting
  • Support vector machine

Fingerprint

Dive into the research topics of 'Application of support vector machines in paying rate forecasting'. Together they form a unique fingerprint.

Cite this