臺灣博碩士論文加值系統

金融投資屬於高度知識密集的產業，隨著金融市場電子化交易技術的成熟，長期下來累積了相當可觀的交易資料，而知識發現法(knowledge discovery)技術的成熟，為金融投資決策支援開啟了另一道曙光。由於金融市場資料多屬時間序列之型態，故用以分析建模的資料維度與數目皆遠較一般離散型資料分析來的複雜。本研究以台灣集中市場加權指數期貨30日之連續K線型態資料為研究對象，提出一個植基於知識發現法的整合性方案，支援分群、分類、預測及視覺化等四項資料探勘的重要工作。為提供投資專家視覺化的資料探勘，本研究採行可將高維度空間資料之複雜非線性關係轉換為低維度之幾何關係的自組織映射圖神經網路進行分群分析，並以輪廓係數法驗證分群結果的效度；接著對映射圖內的型態與當時的走勢資料進行比對以確立其買賣訊號的分類歸屬與交易策略，並根據每群的前24天走勢資料預測後6天的漲跌方向及範圍，評估所制定的交易策略之績效。有別於現行相關研究，本研究將致力於改善投資人最需要的買進賣出訊號的準確度外，亦希望能提昇每次交易的獲利能力。本研究成果可提供建立一套智慧型投資策略決策支援系統，輔助基金經理人、代客操作業者、四大基金操盤人進行投資決策，而專業投資決策者亦可依據本研究所探勘出來的投資決策知識以驗證或修正其內隱知識。

Financial investment is a knowledge-intensive industry. In the past years, with the electronic transaction technology advances, vast amount of transaction data have been collected and the emergence of knowledge discovery technology sheds light toward building up a financial investment decision support system. Data of financial markets are essentially time-series which bring more challenges than the traditional discrete data for uncovering the hidden knowledge. In this research, Taifex Index in Taiwan Futures Exchange K-chart patterns as the target dataset, we tackle with these challenges by proposing an integrated solution on the basis of knowledge-discovery methodology which supports four important tasks of data mining: clustering, classification, forecasting and visualization. In order to provide a decision maker the functionality of visualization, this project utilizes self-organization map that can transform high- dimensional, complicated, and nonlinear data onto low-dimensional ones with topology preservation. For clustering, the silhouette coefficient algorithm are applied to validate the clusters. Following, the trading signals are classified by performing pattern-match with K-Chart patterns in the trained SOM and the sliding-window data. Finally, the closing price in the next day is predicted based on the first 24 days pattern. In contrast to related work, we not only endeavor to improve the accuracy of classification of trading signals, we also are in an attempt to maximize the profits of trading. The resulting intelligence investment decision support system can help fund managers and investment decision-makers of national stable funds make the profitable decision. In addition, financial experts can benefit from the ability of verifying or refining their tacit investment knowledge offered by the uncovered knowledge.

第一章 緒論1
第一節 研究動機與背景1
第二節 研究目的2
第三節 研究限制4
第四節 研究架構5
第二章 文獻探討6
第一節 知識發現法6
第二節 資料探勘6
第三節 K線理論8
第四節 自組織映射圖神經網路10
第五節 輪廓係數集群效度驗證12
第六節 交易所買賣基金( Exchange Traded Fund, ETF )15
第七節 價格預測文獻20
第三章　研究方法22
第一節 研究流程22
第二節 樣本資料說明23
第三節 自組織映射圖神經網路26
第四節 分群效度驗證30
第五節 台灣加權股價指數現貨與期貨間之相關性檢定33
第四章 實驗結果35
第一節 買賣訊號評估35
第二節 交易策略的制定36
第三節 獲利能力與風險衡量之指標介紹39
第四節 績效評估43
第五章　台指期貨當沖交易決策支援系統47
第一節 即時系統實作技術介紹47
第二節 台指期貨當沖交易決策支援系統研究方法47
第三節 台指期貨當沖交易決策支援系統績效評估52
第三節 台指期貨當沖交易決策支援系統於ETF套利上之應用55
第六章 結論57
第一節 結論57
第二節 對後續研究者之建議58
參考文獻………………………………………………………………..60

[1]林成、楊馥聰，K棒兵法，建安出版社，pp.53, 2002
[2]葉日武，現代投資學-原理、技巧與應用，前程企業，2000, pp.220~221
[3]廖廣毅，以類神經網路預測股價指數漲跌，元智大學工工所碩士論文，民國88 年。
[4]劉穎峰，2000，交易所買賣基金在台灣發行之可行性研究，中山大學，碩士論文
[5]蔡文賢，”台灣實施隔週休二日制度對股票報酬率之影響”，亞太會計與財務研究研討會論文集，2000年3月11日。
[6]簡辰丞，結合MACD與類神經模糊技術之股票預測模型─以臺灣金融股為例，靜宜大學，碩士論文
[7]A.K. Jain, “Data Clustering: a review,” ACM Computing Surveys, Vol.31, Issue 3, 1999, pp.264-323.
[8]A.-O. Boudraa, “Dynamic estimation of number of clusters in data sets,” Electronics Letters, Vol. 35, No. 19, 1999, pp. 1606-1608.
[9]B. K. Wong, T. A. Bodnovich, and Selvi, Y., “Neural Network Applications in Business: A Review and Analysis of the Literature,” Decision Support Systems, Vol. 19, 1997, pp. 301-320.
[10]C. B. Apte, B. Liu, E. Pednault and P. Smyth, “Business applications of data mining,” Communications of the ACM, Vol. 45, No. 8, 2002, pp. 49-53.
[11]C. P. Rainsford and J. F. Roddick, “Database Issues in Knowledge Discovery and Data Mining,” Aust. J. Inf. Syst., Vol. 6, No. 2, In Press, 1999.
[12]C. Zopounidis, C., M. Doumpos, and N. F. Matsatsinis, “On the use of Knowledge-based Decision Support Systems in Financial Management: A Survey,” Decision Support Systems, Vol. 20, 1997, pp. 259-277.
[13]D. M. Culters, M. J. Poterba and H. S. Lawrence, “What Move Stock Price?” The Journal of Portfolio Management 15, 1989.
[14]D. Pyle, Data preparation for data mining, Morgan Kaufmann publishers, Inc. San Francisco, California, 1999.
[15]F. Murtagh and A. Aussem, “Using the Wavelet Transform for Multivariate Data Analysis and Time Series Forecasting”, Proc. IFCS''96, Kobe, Springer-Verlag.
[16]H. He and S. H. Chen, “Searching Financial Patterns with Self-Organizing Maps,” in Processing of 3rd International Conference on Computer Vision, Pattern Recognition, and Image Processing, Volume II, 2002, pp.968-976.
[17]J. P. Bigus, “Data Mining with Neural Networks”, McGraw-Hill, 1996.
[18]K. N. Pantazopoulos, L. H. Tsoukalas, N. G., Bourbakis, M. J. Brun, E. N. Houstis, “Financial Prediction and Trading Strategis Using Neuro Fuzzy Approaches,“ IEEE Transactions Systems, man and cybernetics─Part B: Cybernetics, Vol.28, No. 4, 1998, pp.520-531.
[19]L. Kaufman and P. J. Rousseeuw, Finding Groups in Data — An Introduction to Cluster Analysis, John Wiley &Sons, New York. 1990.
[20]M. F. Jan, S. Andrew, and B. Whinston, “A Web-Based Financial Trading System,” IEEE 1999.
[21]M.-S. Chen, J. Han, and P. S. Yu, “Data Mining: An Overview from a Database Perspective”, IEEE Trans. on Knowledge and Data Engineering, Vol. 8, No. 6, pp. 866-883, 1996.
[22]N. R. Pal and J. C. Bezdek, “On Cluster Validity for the Fuzzy c-Means Model,” IEEE Transactions on Fuzzy Systems, Vol. 3, No. 3, August 1995, pp. 370-379.
[23]R.Tsaih, Y. Hsu, C.C.Lai, “Forecasting S & P 500 stock index futures with a Hybird AI System”, Decision Support System 23, pp. 161-174, 1998.
[24]S.-T. Li, “A Web-aware Interoperable Data Mining System,” Expert Systems with Applications, Vol. 22, pp. 135-146, 2002.
[25]S. T. Yuan and M. Kuan, “Comprehensive and Personalized Stock Performance Prediction, ” Journal of Information management, Vol. l, Issue 2, 2002, pp.211-239.
[26]T. Kohonen, 1997, Self-Organizing Maps, Springer, Germany.
[27]U.M. Fayyad et al., 1996, “ Advances in Knowledge Discovery and Data Mining”, AAAI Press/The MIT Press, Menlo Park.
[28]U.M. Fayyad, G. P. Shapiro, and P. Smyth, “From data Mining to Knowledge Discovery: An Overview”, Advances in Knowledge Discovery and Data Mining, MA AAAI/ MIT Press, 1996, pp. 1-36.
[29]Ultsch and C. Vetter, “Self-Organizing-Feature-Maps versus Statistical Clustering Methods: A Benchmark”, Research Report 0994, University of Marburg, FG Neuroinformatik & Knstliche Intelligenz, 1993.
[30]Wolberg, John R., Expert trading systems: modeling financial markets with kernel regression. NY: John Wiley & Sons, 2000.
[31]Y.T.Lee, J.C.Lin, Y.J.Liu, “Trading patterns of big versus small players in an emerging market: An empirical analysis.” Journal of Banking and Finance 23, pp701-725, 1999.
[32]Z. Zhanggui, H. Yan and A. M.N, “A New Stock Price Prediction Method Based on Pattern Classification,” IEEE 1999.