臺灣博碩士論文加值系統

以股票股價分析而言，目前有許多關於股價分析的研究。其目的為使投資者有更多的資訊以進行決策分析。技術指標為股價走勢分析方法之一種。為了解決因技術指標所造成資料分析的困難以及維持資料分類規則的準確性，本研究主要目的是利用粗略集合論(Rough Set Theory)結合支援向量機(Support Vector Machines)作為決策分析的工具，以處理股價的不確定性問題，並建立資料間之相關性以作為決策之依據。針對粗略集合論中屬性值屬於連續數值的處理問題，本研究將利用自組織映射圖網路(Self-organizing map, SOM)對每一個屬性進行分群，並用替代值取代先前的數據。此外，粗略集合論所產生的決策規則於結合支援向量機後，使決策規則做調整，將會產生明確的決策指標。研究針對技術指標分析能力的不完整，利用粗略集合論結合技術指標使用方式，使投資者明確地知道股價漲跌幅度。

The problem studied here was about the stock price prediction for use of investors.Technical analysis is mainly concerned with market indicators.These technical indicators look at the trend of price indices and individual securities.In order to solve because difficulty of analysis that technical indicator causes and categorised accuracy，Application of rough set theory(RST) and Support Vector Machines(SVM) to set up decision system.In order to deal with uncertain problem of Stock price , set up dependence of materials in order to as decision maker(DM).Application of Self-organizing map(SOM) to discretize the continuous attributes in reconstructed decision table for the succeeding rough sets processing. In our experiments,utilize SVM to choose the best parameter association to adjust decision rule,enable improving its decision rule and predicting ability.Utilize RST to combine the occupation mode of the technical indicator,let investors know the range of ups and downs of the stock price clearly .

授權書 iii
中文摘要 iv
ABSTRACT v
誌謝 vi
目錄 vii
圖目錄 ix
表目錄 x

第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 研究流程 2
第二章 文獻探討 4
2.1 技術指標分析 4
2.2 粗略集合理論 9
2.3自組織映射圖網路 13
2.4支援向量機支援向量機(Support Vector Machions; SVMs) 14
第三章 研究方法 20
3.1 研究架構 20
3.2組織映射圖網路結構（Self-Organizing Map，SOM） 21
3.3略集合理論模型(Rough-Sets Theory,RST) 22
3.4支援向量機模型(Support Vector Machions; SVMs) 29
第四章 預測股價實例 31
4.1預測公司股價實例一(電子面板公司奇美電子) 31
4.2預測公司股價實例二(中國鋼鐵公司) 37
4.3預測公司股價實例三(半導體台積電公司) 43
4.4預測公司股價實例四(統一食品公司) 46
4.5預測公司股價實例五(台塑化學公司) 48
4.6 結果分析與討論 51
第五章 結論及末來研究方向 53
5.1 結論 53
5.2 末來研究方向 54
參考文獻 55

[1]朱富春，股價分析，聯經出版有限公司，民國67 年。
[2]杜金龍，技術分析在台灣股市應用訣竅，金錢文化，民國87 年。
[3]Ahn,B.S, S.S Cho,C.Y Kim, “The integrated methodology of rough set and artificial neural network for business failure prediction”, Expert System With Applications 18(2000) 65–74
[4]Baltzersen, J.K., “An attempt to predict stock market data:a rough sets approach.” Diploma Thesis, Knowledge Systems Group, Department of Computer Systems and Telematics,The Norwegian Institute of Technology, University of Trondheim(1996).
[5]Bazan, J.G., Skowron, A., Synak, P., “Market data analysis: A rough set approach.”,ICS Research Reports ,Warsaw University of Technology(1994).
[6]Dimitras,A.I, R.Slowinski,R.Susmaga,C.Zopounidis”, “Business failure prediction using rough set”,European Journal of Operational Research 114 (1999) 263–280.
[7]Dimitras, A.I., Slowinski, R., Susmaga, R., Zopounidis, C., “Business failure prediction using rough sets.” European Journal of Operational Research 114, (1999) 263–280.
[8]Dimitras, A.I., Zanakis, S.H., Zopounidis, C., “A survey of business failure with an emphasis on prediction methods and industrial applications.”, European Journal of Operational Research 90 (1996) 487–513.
[9]Golan, R., “Stock market analysis utilizing rough set theory.”,Ph.D. Thesis, Department of Computer Science, University of Regina,Canada(1995).
[10]Greco, S., Cascio, L.S., Matarazzo, B., “Rough set approach to stock selection: An application to the Italian market.” In: Bertocchi, M., Cavalli, E., Komlosi, S. (Eds.),Modelling Techniques for Financial Markets and Bank Management. Physica-Verlag, Heidelberg,(1996)192–211.
[11]Hashemi, R.R., L.A. Le Blanc, C.T. Rucks, A. Rajaratnam,“A Hybrid Intelligent System for Predicting Bank Holding Structures”,European Journal of Operational Research vol.109, (1998)390-402.
[12]I. Beltzer Abraham, Tadanobu Sato,“Neural classification of finite elements” , Computers and Structures ,81 , (2003)2331–2335.
[13]Kim, K.J., “Financial time series forecasting using support vector machines”, Neur computing,55, (2003)307-319.
[14]Khoo,Li-Pheng, Lian-Yin Zhai, “A prototype genetic algorithm-enhanced rough set-based rule induction system”, Computer in Industry 46,(2001) 95–106.
[15]Kohonen, T.. “Self-organized formation of topologically correct feature maps”. Biological Cybernetics, 43, (1982)59-69.
[16]Li,Renpu, Zheng-ou Wang , “Mining classification rules using rough sets and networks”, European Journal of Operational Research 157,(2004) 439–448.
[17]Mrozek, A., Skabek, K., “Rough sets in economic applications”, In: Polkowski, L., Skowron, A. (Eds.), “Rough Sets in Knowledge Discovery”, vol. 2. Physica-Verlag,Wurzburg,(1998)238–271,Chapter 13.
[18]Pawlak，Zdzislaw , “Rough Sets”, International Journal of Computer and Information Science, Vol. 11, No. 5,(1982)341-356.
[19]Ruggiero, M., “Rules are made to be traded.”, AI in Finance (Fall),(1994)35–40.
[20]Ruggiero, M., “How to build a system framework.”,Futures 23,(1994)50–56.
[21]Shawe-Taylor,John, John C. Platt, Nello Cristianini,” Large Margin DAGs for Multiclass Classification”, S.A. Solla, T.K. Leen and K.-R. M¨uller (eds.), (2000)547–553, MIT Press.
[22]Shen, Lixiang, Han Tong Loh, “Apply rough set to market timing decisions”,Decision support systems , (2004)583–597.
[23]Skalko, C., “Rough sets help time the OEX.” Journal of Computational Intelligence in Finance 4(6), (1996)20–27.
[24]Slowinski, R., Stefanowski, J.,“Rough classification with valued closeness relation. In: Diday, E. et al. (Eds.), New Approaches in Classification and Data Analysis”. Springer,Berlin, (1994)482–488.
[25]Slowinski, R., Zopounidis, C., “Rough-set sorting of firms according to bankruptcy risk.”, In: Paruccini, M. (Ed.), Applying Multiple Criteria Aid for Decision to Environmental Management. Kluwer Academic Publishers, Dordrecht,(1994)339–357.
[26]Slowinski, R., Zopounidis, C., “Application of the rough set approach to evaluation of bankruptcy risk. International Journal of Intelligent Systems in Accounting:”, Finance & Management 4(1),(1995)27–41.
[27]Tay,Francis E.H, Lixiang Shen, “Economic and financial prediction using rough set model”, European Journal of Operational Research 141(2002) 641–659.
[28]Tay, F.E.H., L.J. Cao, “Application of support vector machines in financial time series forecasting”, OMEGA, 29, (2001)309- 317.
[29]Thissen, U., R. Brakel, A.P. Weijer, W.J. Melssen and L.M.C. Buydens, “Using support vector machines for time series prediction,” Chemometrics and Intelligent Laboratory Systems, 69,(2003)35-49.
[30]Trafalis, T. B. & Ince, H. Y., “Support Vector Machine for Regression and Application to Financial Forecasting. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks”, IEEE Computer Society, Vol. 6, (2000)348-353.
[31]Ziarko, W., Golan, R., Edwards, D., “An application of datalogi c/R knowledge discovery tool to identify strong predictive rules in stock market data.”, In: Proceedings of AAAI Workshop on Knowledge Discovery in Databases,Washington,DC,(1993) 89–101.
[32]Zheng,Zheng, Guoyin Wang, Yu Wu, “Object’s Combination Based Simple Computation of Attribute Core”, Proceedings of the 2002 IEEE, International Symposium on Intelligent Control, Vancouver, Canada, Oct. 27-30,(2002)514-519.