現在位置首頁 > 博碩士論文 > 詳目
  • 同意授權
論文中文名稱:結合支援向量機與粒子群最佳化探索台灣股市預測模式 [以論文名稱查詢館藏系統]
論文英文名稱:Combining SVM and PSO to explore the prediction models of Taiwan Stock Market [以論文名稱查詢館藏系統]
院校名稱:臺北科技大學
學院名稱:管理學院
系所名稱:資訊與運籌管理研究所
畢業學年度:99
出版年度:100
中文姓名:陳博文
英文姓名:Po-wen Chen
研究生學號:98938016
學位類別:碩士
語文別:中文
口試日期:2010-06-22
論文頁數:107
指導教授中文名:翁頌舜
口試委員中文名:楊欣哲;吳瑞堯
中文關鍵詞:支援向量機粒子群最佳化投資預測
英文關鍵詞:Support Vector MachineParticle Swarm Optimizationfinancial prediction
論文中文摘要:本研究在於探討如何應用支援向量機(Support Vector Machine)在台灣股市中,分別採用分類(Classification)與迴歸(Regression)技術建立個股投資預測模型,並且輔以粒子群最佳化(Particle Swarm Optimization)進行參數最佳化與變數篩選。一直以來台灣股市被認為極難分析且預測,所以本研究希望能夠有效地整合財務基本面與技術分析面的資訊,以建立穩健的投資預測模式。
本研究分析模式為根據公司各季所公布的財務報表與自行計算出的技術指標進行預測。在採用台灣股市歷史資料進行投資模擬後,實證本研究的方法可以產生不錯的獲利曲線。同時,本研究所得的模擬結果經過分析,也證明優於類神經網路預測模式或是買進及持有的投資策略。因此,本研究認為在同時整合財務基本面與技術分析面的資訊下,使用支援向量機和粒子群最佳化建立個股投資預測模型,不失為一種可以有效獲利而且相當穩健的投資策略。
論文英文摘要:This study is to explore how to apply the Support Vector Machine (SVM) method to build the prediction model from classification and regression techniques for individual stock in Taiwan Stock Market and leverage Particle Swarm Optimization (PSO) for parameter optimization and feature selection. Usually researchers think that it’s difficult to have an efficient prediction about the trends of Taiwan Stock Market. It’s the goal of this study to create a robust financial forecast model based on both fundamental and technical analysis information.
This research uses quarterly financial reports and simple technical indexes as independent variables for financial prediction. The empirical results show that the performance of PSO+SVM is much better than that of artificial neural network or Buy & Hold investing strategy. Therefore, it is proven to be an efficient and robust investing strategy by combining both SVM and PSO data mining techniques.
論文目次:目 錄

摘 要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究背景動機 1
1.2 研究目的 1
1.3 研究流程 2
1.4 論文章節結構 3
第二章 文獻回顧 5
2.1 文獻整理方向 5
2.2 一般股市相關文獻整理 6
2.3 支援向量機與支援向量迴歸 8
2.4 粒子群最佳化 13
第三章 研究方法 16
3.1 研究方向 16
3.2 分析模型及研究架構 17
3.3 研究變數 19
3.3.1 基本面財務指標的自變量 19
3.3.2 技術面指標的自變量 20
3.3.3 技術指標定義 20
3.3.4 應變量 22
3.3.5 分析資料第一階段前處理 23
3.3.6 分析資料第二階段前處理 26
3.4 訓練資料與測試資料定義 26
3.5 實作程式 27
3.6 PSO編碼方式及設定參數 27
3.7 適應函數 28
3.8 Wrapper 運作模式 29
3.9 Vote模型 30
3.10 類神經網路模型 31
3.11 投資組合定義 31
第四章 實驗結果及數據分析 32
4.1 資料樣本 32
4.2 實驗結果產生過程 33
4.3 訓練階段的適應函數值 33
4.4 測試階段的適應函數值 35
4.5 平均投資績效比較 37
4.6 投資組合模擬 39
4.7 最佳化參數 42
第五章 研究結論 44
5.1 研究發現 44
5.2 研究結論與建議 46
5.3 研究限制以及研究貢獻 48
5.4 未來研究方向 50
參考文獻 51
附錄 54
A. 財務指標定義 54
B. 投資績效成果 69
B.1買進及持有績效 69
B.2 PSO+SVM 投資績效成果 70
B.3 PSO+SVR 投資績效成果 71
B.4 VOTE模型投資績效成果 72
B.5 BPNN 投資績效成果 73
C. 實驗數據資料表格 75
論文參考文獻:[1] Atsalakis G., and Valavanis K., "Surveying stock market forecasting techniques-Part II: Soft computing methods," Expert Systems with Applications , 2009, 36:5932-5941.
[2] Banks A., Vincent J., and Anyakoha C., "A review of particle swarm optimization. Part I: background and development," Natural Computing, 2007, 6:467-484.
[3] Banks A., Vincent J., and Anyakoha C., "A review of particle swarm optimization. Part II: hybridisation, combinatorial, multicriteria and constrained optimization, and indicative applications," Natural Computing, 2008, 7:109-124.
[4] Burges C., "A tutorial on support vector machines for pattern recognition," Data mining and knowledge discovery , 1998, 2:121-167.
[5] Cao Q., Leggio K., and Schniederjans M., "A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market," Computers & Operations Research , 2005, 32:2499-2512.
[6] Chen W., and Shih J., "A study of Taiwan's issuer credit rating systems using support vector machines," Expert Systems with Applications , 2006, 30:427-435.
[7] Cura T., "Particle swarm optimization approach to portfolio optimization. Nonlinear Analysis: Real World Applications," 2009, 10:2396-2406.
[8] Eakins S., and Stansell S., "Can value-based stock selection criteria yield superior risk-adjusted returns: an application of neural networks," International review of financial analysis , 2003, 12:83-97.
[9] Gilli M., and Roko I., "Using Economic and Financial Information for Stock Selection," Computational Management Science:317, 2008, V335.
[10] Grosan C., and Abraham A., "Hybrid evolutionary algorithms: Methodologies, architectures, and reviews," Hybrid Evolutionary Algorithms, 2007, 1-17.
[11] Hann T., and Steurer E., "Much ado about nothing? Exchange rate forecasting: Neural networks vs. linear models using monthly and weekly data," Neurocomputing , 1996, 10:323-339.
[12] Hsu C., Chang C., and Lin C., "A Practical Guide to Support Vector Classification," 2003.
[13] Huang C., Chen M., and Wang C., "Credit scoring with a data mining approach based on support vector machines," Expert Systems with Applications , 2007a, 33:847-856.
[14] Huang C., Yang D., and Chuang Y., "Application of wrapper approach and composite classifier to the stock trend prediction," Expert Systems with Applications , 2008, 34:2870-2878.
[15] Huang W., Lai K., Nakamori Y., Wang S., and Yu L., "Neural networks in finance and economics forecasting," International Journal of Information Technology and Decision Making , 2007b, 6:113-140.
[16] Kennedy J., and Eberhart R., "Particle swarm optimization," Perth, Australia, 1995, pp. 1942-1948.
[17] Kim K., "Financial time series forecasting using support vector machines," Neurocomputing , 2003, 55:307-319.
[18] Kuo I., "An improved method for forecasting enrollments based on fuzzy time series and particle swarm optimization," Expert Systems with Applications , 2009, 36:6108-6117.
[19] Lin C., and Chang C., "LIBSVM: a library for support vector machines," 2001.
[20] Lin S., Ying K., Chen S., and Lee Z., "Particle swarm optimization for parameter determination and feature selection of support vector machines," Expert Systems with Applications, 2008, 35:1817-1824.
[21] Marinakis Y., Marinaki M., Doumpos M., and Zopounidis C., "Ant colony and particle swarm optimization for financial classification problems," Expert Systems with Applications , 2009, 36:10604-10611.
[22] Olson D., and Mossman C., "Neural network forecasts of Canadian stock returns using accounting ratios," International Journal of Forecasting , 2003, 19:453-465.
[23] Quah T., "DJIA stock selection assisted by neural network," Expert Systems with Applications , 2008, 35:50-58.
[24] Ren N., Zargham M., and Rahimi S., "A decision tree-based classification approach to rule extraction for security analysis," International Journal of Information Technology & Decision Making, 2006, 5:227-240.
[25] Scholkopf B., and Smola A., "Learning with kernels Citeseer,", 2002.
[26] Su C., and Yang C., "Feature selection for the SVM: An application to hypertension diagnosis," Expert Systems with Applications , 2008, 34:754-763.
[27] Tay F., and Cao L., "Application of support vector machines in financial time series forecasting," Omega , 2001, 29:309-317.
[28] Vapnik V., "The nature of statistical learning theory," Springer Verlag, 2000.
[29] Yu L., Chen H., Wang S., and Lai K., "Evolving least squares support vector machines for stock market trend mining," Evolutionary Computation, IEEE Transactions on , 2009, 13:87-102.
[30] Zhang J., Zhang J., Lok T., and Lyu M., "A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training," Applied Mathematics and Computation , 2007, 185:1026-1037.
論文全文使用權限:同意授權於2011-08-04起公開