DocumentCode :
3519839
Title :
Application of Support Vector Machines in Paying Rate Forecasting
Author :
Chong, Wu ; Pu, Chen
Author_Institution :
Sch. of Manage., Harbin Inst. of Technol.
fYear :
2006
fDate :
5-7 Oct. 2006
Firstpage :
1494
Lastpage :
1497
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
Keywords :
Gaussian processes; backpropagation; economic forecasting; feedforward neural nets; financial data processing; mean square error methods; support vector machines; time series; Gaussian function; SVM; feed-forward backpropagation neural network; financial time series forecasting; kernel function; mean absolute percent error; paying rate index prediction; root mean square error; support vector machine; Backpropagation; Economic forecasting; Feedforward neural networks; Feedforward systems; Financial management; Neural networks; Predictive models; Support vector machines; Technology forecasting; Technology management; BP neural network; Financial time series; Forecasting; Support vector machine;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Management Science and Engineering, 2006. ICMSE '06. 2006 International Conference on
Conference_Location :
Lille
Print_ISBN :
7-5603-2355-3
Type :
conf
DOI :
10.1109/ICMSE.2006.314265
Filename :
4105128
Link To Document :
بازگشت