Stock Return Forecast with LS-SVM and Particle Swarm Optimization

摘要：

Stock return forecast has been an important issue and difficult task for both shareholders and financial professionals. To tackle this problem, we introduce Least Square Support Vector Machine (LS-SVM), an improved algorithm that regresses faster than standard SVM, and Dynamic Inertia Weight Particle Swarm Optimization (W-PSO), that outperform standard PSO in parameter selection. The work of this paper is as following: First, forecast daily stock Return of Shanghai Security Exchanges of China using Back Propagation Neural Network (BPNN) and LS-SVM. Secondly, forecast the stock return using LS-SVM optimized by W-PSO. Finally, make a comparative analysis of the three algorithms. We reached conclusion that, in terms of forecast accuracy, LS-SVM outperforms BPNN, and when LS-SVM is optimized by W-PSO, the best result is achieved.

关键词： Stock Return Forecast Least Square Support Vector Machines Dynamic Inertia Weight Particle Swarm Optimization

作者: Wei Shen Yunyun Zhang Xiaoyong Ma

作者单位: School of Business and Administration North China Electric Power University Beijing, 102206, China Department of Economics and Administration North China Electric Power University Baoding, 071003, Ch

会议类型: 国际会议

会议名称: The Second International Conference on Business Intelligence and Financial Engineering(BIFE 2009)(第二届商务智能与金融工程国际会议)

会议地点: 北京

会议语种:英文

页码: 143-147

在线出版日期: 2009-07-24（万方平台首次上网日期，不代表论文的发表时间）