Share Email Print
cover

Proceedings Paper

Fund trend prediction based on least squares support vector regression
Author(s): Yilan Bao
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

It is well-known that accurate prediction of fund trend is very important to get high profits from fund market. In the paper, least squares support vector regression (LSSVR) is adopted to predict fund trend. LSSVR higher the non-linear prediction ability than other prediction methods .The trading price of fund "kexun" from 2007-3-1 to 2007-3-30 is used as our experimental data, and the trading price from 2007-3-26 to 2007-3-30 is used as the testing data. The forecasting results of BP neural network and least squares support vector regression are given. The experimental results show that the forecasting values of LSSVR are nearer to actual values that those of BP neural network.

Paper Details

Date Published: 13 January 2012
PDF: 4 pages
Proc. SPIE 8350, Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies, 83502S (13 January 2012); doi: 10.1117/12.920286
Show Author Affiliations
Yilan Bao, Dalian Maritime Univ. (China)


Published in SPIE Proceedings Vol. 8350:
Fourth International Conference on Machine Vision (ICMV 2011): Computer Vision and Image Analysis; Pattern Recognition and Basic Technologies
Safaa S. Mahmoud; Zhu Zeng; Yuting Li, Editor(s)

© SPIE. Terms of Use
Back to Top