臺灣博碩士論文加值系統

股價的預測有助於投資者做出正確的投資決策。然而，如何從大量的股價波動中，推導出有效的預測法則，一直被視為最大的挑戰。本論文的目標即在於此，我們的方法以K線表示股價波動，特殊的股價波動表示成連續出現、不同型態的K線序列。透過分析這些K線序列在不同股價變化區間對未來股價的影響，我們可以產生有效法則以預測未來的走勢，當最近的股價波動滿足法則的條件時，我們便建議投資者買進或賣出股票，並同時監測股價的後續波動，於適當的時機建議投資者獲利或停損出場。實驗結果顯示，我們的法則可達到平均71%的預測準確度。在模擬的交易操作中，我們的投資策略確實幫助投資者獲利，即使預設停損點，在所有投資建議裡，獲利的比例平均仍可達60%。

The prediction of stock prices helps the investor to make a good decision. However, the discovery of effective rules from the stock data is the greatest challenge, which is also the goal of this thesis. Our approach adopts K-charts to represent the stock oscillation and a particular oscillation is a consecutive sequence of K-charts with various types. With the analysis of how these sequences influence the future stock prices in different price intervals, we can create effective rules for future trend prediction. When the recent prices satisfy the antecedents of our rules, we suggest the investor to buy or sell the stock and continue to monitor the stock oscillation. Moreover, at the right moment, we also suggest the investor to make a profit or stop a loss. Experiment results show that our rules can achieve the precision 71% on average. In the simulated operations, our investment strategy indeed helps the investor to make a profit. Even when the stop-loss point is set, among all the suggestions, the percentage of making a profit can still achieve 60% on average

目錄
摘要............................................................................................................................................................... II
ABSTRACT ...................................................................................................................................................... III
誌謝.............................................................................................................................................................. IV
目錄................................................................................................................................................................V
附表目錄...................................................................................................................................................... VI
附圖目錄.....................................................................................................................................................VII
第一章 緒論.............................................................................................................................................. 1
第二章 相關研究.....................................................................................................................................13
第三章 投資法則之推導...........................................................................................................................16
3.1 K 線型態.....................................................................................................................................16
3.2 K 均線序列.................................................................................................................................19
3.3 投資法則及其推導.......................................................................................................................19
第四章 查詢處理及建議投資策略...........................................................................................................23
4.1 查詢處理.....................................................................................................................................23
4.2 停損策略.....................................................................................................................................26
4.3 投資策略.....................................................................................................................................27
4.3.1 獨立式的投資策略.......................................................................................................................28
4.3.2 相依式的投資策略.......................................................................................................................30
第五章 實驗.............................................................................................................................................44
5.1 法則的檢驗.................................................................................................................................45
5.2 獨立式投資策略獲利...................................................................................................................48
5.3 相依式投資策略觀察...................................................................................................................49
第六章 結論及未來工作...........................................................................................................................53
參考文獻.......................................................................................................................................................54




附表目錄
表一、KMS1 的int 天漲跌幅初步計數............................................................... 20
表二、KMS 1 的int 天漲跌一覽表...................................................................... 21
表三、實驗參數符號及意義ㄧ覽....................................................................... 44
表四、2008 年至2009 年各漲跌幅獲利情形..................................................... 49




附圖目錄
圖一、K 線............................................................................................................ 4
圖二、K 線的種類................................................................................................. 5
圖三、鴻海K 線圖：2002/5/21~2002/6/3............................................................... 6
圖四、鴻海收盤價時間序列：1999/6/17~1999/7/7 .............................................. 7
圖五、用K 線預測股價波動................................................................................. 7
圖六、K 線序列與移動平均線的位置關係.......................................................... 9
圖七、K 線於高股價和低股價的型態差異........................................................ 13
圖八、依照K 線外觀的初步分類....................................................................... 16
圖九、處理查詢流程.......................................................................................... 24
圖十、停損機制設定.......................................................................................... 27
圖十一、獨立式的投資策略............................................................................... 29
圖十二、買進買進的情況.............................................................................. 32
圖十三、買進賣出的情況.............................................................................. 36
圖十四、新建議點兩個以上............................................................................... 42
圖十五、法則在各季精確度的表現................................................................... 46
圖十六、法則在各季符合率的表現................................................................... 47
圖十七、法則在各季服務率的表現................................................................... 48
圖十八、平均的單季投資報酬率....................................................................... 51
圖十九、平均每季的累積年投資報酬率........................................................... 52

參考文獻
[1] J. Bollinger, “Bollinger on Bollinger Bands,” New York: McGraw-Hill, fist edition, 2001.
[2] P.C. Chang, C.H. Liu, J.L. Lin, C.Y. Fan, and C.S.P. Ng “A Neural Network with a Case Based Dynamic Window for Stock Trading Prediction,” Expert Systems and Applications, 36(3), pp. 6889-6898, 2009.
[3] H.H. Chu, T.L. Chen, C.H. Cheng, and C.C. Huang, “Fuzzy Dual-factor Time-series for Stock Index Forecasting,” Expert Systems and Applications, 36(1), pp. 165-171, 2009.
[4] R.D. Edwards, “Technical Analysis of Stock Trends,” Chemical Rubber Company, 9th edition, 2007.
[5] C.H. Lee and A. Liu, “A Financial Decision Supporting System Based on Fuzzy Candlestick Patterns,” Joint Conference on Information Sciences, 2006.
[6] R.W. Hafer, “The Stock Market,” Greenwood Press, 2007.
[7] S. Hoover, “Stock Valuation: An Essential Guide to Wall Street's Most Popular Valuation Models,” New York: McGraw-Hill, 2006.
[8] T. Kamo and C.H. Dagli, “Hybrid Approach to the Japanese Candlestick Method for Financial Forecasting,” Expert Systems and Applications, 36(3), pp. 5023-5030, 2009.
[9] S.T. Li and S.C. Kuo, “Knowledge Discovery in Financial Investment for Forecasting and Trading Strategy through Wavelet-based SOM Networks,” Expert Systems and Applications, 34(2), pp. 935-951, 2008.
[10] C.L. Lu and T. Chen, “A Study of Applying Data Mining Approach to The Information Disclosure for Taiwan's Stock Market Investors,” Expert Systems and Applications, 36(2), pp. 3536-3542, 2009.
[11] G.L. Morris, “Candlestick Charting Explained: Timeless Techniques for Trading Stocks and Futures,” New York: McGraw-Hill, 1995.
[12] S. Nisson, “Japanese Candlestick Charting Techniques: A Contemporary Guide to The Ancient Investment Techniques of The Far East (2nd ed.),” New York Institute of Finance, 2001.
[13] PChome Stock Market, http://pchome.syspower.co m.tw/ [Accessed: July 8 2010].
[14] E.A. Peterson and P. Tang, “A Hybrid Approach to Mining Frequent Sequential Patterns,” ACM Southeast Regional Conference, 2009.
[15] G. Rachlin and M. Last, “Predicting Stock Trends with Time Series Data Mining and Web Content Mining,” Advances in Web Intelligence and Data Mining, Studies in Computational Intelligence, Vol. 23, pp. 181-190, 2006.
[16] R.P. Schumaker and H. Chen, “Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFin Text System,” ACM Transactions on Information Systems, 27(2), 2009.
[17] X. Tang, C. Yang, and J. Zhou, “Stock Price Forecasting by Combining News Mining and Time Series Analysis,” Web Intelligence, pp. 279-282, 2009.
[18] M.L. Vásquez, F.G. Osorio, and D.H. Losada, “Mining Candlesticks Patterns on Stock Series: A Fuzzy Logic Approach,” Advanced Data Mining and Applications, pp. 661-670, 2009.
[19] J. Wang, B. Fan, and T. Wang, “Statistical Analysis and Data Analysis of Stock Market by Interacting Particle Models,” Journal of Computers,
3(12), pp. 11-18, 2008.
[20] H. Wu, B. Salzberg, and D. Zhang, “Online Event-driven Subsequence Matching over Financial Data Streams,” ACM SIGMOD International Conference on Management of Data, pp. 23-34, 2004.
[21] Yahoo Stock Market, http://tw.stock.yahoo.com/ [Accessed: July 8 2010].
[22] Y. Yang, “Pattern Recognition Based on Support Vector Machine: Computerizing Expertise for Predicting the Trend of Stock Market,” Computer Science and Information Engineering, pp. 60-66, 2009.