基於SVR及SVM的智慧型分類器設計應用於預測股票價格漲跌趨勢

Design of Intelligent Classifiers Based on SVR and SVM for Stock Price Trend Prediction

洪嘉鴻(Chia-Hung Hung)

指導教授 ： 蔡鴻旭

國立虎尾科技大學/管理學院/資訊管理研究所/碩士(2013年)

摘要

本論文提出設計新的智慧型分類器來進行股票價格漲跌趨勢預測，首先使用支持向量迴歸(Support Vector Regression, SVR)預測股價漲跌幅並利用粒子族群最佳化演算法(Particle Swarm Optimization, PSO)來最佳化SVR即挑選SVR近似最佳參數組，以提高預測之準確性，接著再利用委員會機器(Committee Machine, CM)再提升股票價格漲跌趨勢的預測效能。本論文使用台灣經濟新報(TEJ)所提供之台灣加權指數、台積電及台灣50等資料為驗證資料，根據實驗結果顯示，本論文提出的智慧型分類器效能優於大部分欲比較的其他分類器。

關鍵字

智慧型分類器 ； 股價預測 ； 粒子族群最佳化演算法 ； 支持向量迴歸 ； 支持向量機 ； 類神經網路

並列摘要

The thesis proposes two prediction schemes for stock price trend. The first scheme first utilizes the support vector regression (SVR) to estimate the stock price rate and then perofrms a classification model for classfying the estimation regression results while forcasting the stock price trend. The second one employs committee machine (CM) to promote the performance of the first scheme. Here the Particle Swarm Optimization (PSO) algorithm is used to optimize these two schemes via searchimg for a nearly optimimal parameter set for each scheme. Three stock price data sets, TAIEX (Taiwan stock exchange capitalization weighted stock index), TSMC (Taiwan Semiconductor Manufacturing Company), and TW50, are used in the evaluation of the proposed schemes. Experimental results show that, in most of cases, the proposed schemes outperform other prediction models under consideration here.

並列關鍵字

stock price forecasting ； Particle Swarm optimization ； neural networks and intelligent algorithms ； support vector machine ； support vector regression ； committee machine

參考文獻

[21] C. F. Huang, B. R. Chang, D. W. Cheng, and C. H. Chang, “Feature Selection and Parameter Optimization of a Fuzzy-based Stock Selection Model Using Genetic Algorithms”, International Journal of Fuzzy Systems, vol. 14, pp. 65-74, 2012.

[1] S. T. Li, Y. C. Cheng, and S.-Y. Lin, “A FCM-based deterministic forecasting model for fuzzy time series,” Computers and Mathematics with Applications, vol. 56, pp. 3052-3063, 2008.

[2] Q. Song and B. S Chissom, “Fuzzy time series and its models,” Fuzzy Sets and Systems, vol.54, pp.269-277, 1993.

[4] Y. K. Kwon and B. -R. Moon, “A hybrid neurogenetic approach for stock forecasting,” IEEE Transactions on Neural Networks, vol. 18, pp. 851-864, 2007.

[5] C. H. Cheng, T. L. Chen, and L. -Y. Wei, “A hybrid model based on rough sets theory and genetic algorithms for stock price forecasting,” Information Sciences, vol. 180, pp. 1610-1629, 2010.