Responsive image
博碩士論文 etd-0121118-150723 詳細資訊
Title page for etd-0121118-150723
論文名稱
Title
利用美國股市改進台灣股市的交易策略
Improving Trading Strategy on Taiwan Stocks with United States Stock Market
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
124
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2018-01-30
繳交日期
Date of Submission
2018-02-21
關鍵字
Keywords
美國股市指數、相似度、交易訊號、基因規劃法、股票投資
trading signal, US stock indices, similarity, gene expression programming, stock investment
統計
Statistics
本論文已被瀏覽 5670 次,被下載 25
The thesis/dissertation has been browsed 5670 times, has been downloaded 25 times.
中文摘要
隨著現代國際企業的蓬勃發展,企業之間經常會有跨國合作的關係,並且相互影響。如何利用美國股市資訊來改進台灣股市投資獲利的研究非常的少。因此,我們研究透過使用美國股市前一天的資訊來改善台灣股市的交易策略。
  我們方法一開始先將台灣股市與美國股市的交易日做對齊。接下來,分別計算台灣投資組合指數(PI)與其中一個美國股市指數(道瓊工業指數(DJIA)、那斯達克綜合指數(NASDAQ)、標準普爾500指數(S&P 500))的相似度。再利用李承翰所提出的方法產生PI或者任何一個美國股市指數的交易訊號。最後,透過相似度的權重計算,再經由多數決的方式決定出PI的共識買賣訊號。
  PI的訓練區間開始於1996年1月4日,至2017年12月29日為止,總共5591天。DJIA、NASDAQ以及S&P 500的訓練區間開始於1996年1月2日,至2017年12月29日為止,總共5539天。我們的交易區間開始於2000年1月4日,至2017年12月29日為止。由實驗結果可得知,我們認定指數組合(PI, DJIA, NASDAQ)結合權重函數W(4)為買賣投資PI的最佳組合。其平均年化報酬率(累積報酬率)達15.03%(1170.42%),明顯優於李承翰之方法的平均年化報酬率13.88%(累積報酬率947.65%)以及buy-and-hold策略的平均年化報酬率9.85%(累積報酬率442.90%)。
Abstract
With the rapid development of modern business, the companies often have cross-border cooperation and influence with each other. There are few researches studying on how to utilize the information of US stock markets to increase investment profit in Taiwan stock market. Therefore, we study the trading strategy improvement with the information of US stock market.

Our method first aligns the trading days between Taiwan and US stock market. Next, the similarity between PI and one of the US stock indices, the Dow Jones Industrial Average (DJIA), NASDAQ composite index (NASDAQ),or Standard & Poor's 500 (S&P 500), is computed, respectively. The trading signals of PI or each US stock index are generated by the method of Lee et al.. Finally, the consensus signals of PI are determined by the majority voting scheme based on the weight, calculated from the similarity.

The training period of PI starts from 1996/1/4 through 2017/12/29, totally 5591 days, and the training period of DJIA, NASDAQ, and S&P 500 starts from 1996/1/2 through 2017/12/29, totally 5539 days. The trading period starts from 2000/1/4 to 2017/12/29. As the experimental results show, index combination (PI, DJIA, NASDAQ) with W(4) is considered to be the best combination for trading PI. Its average annualized return (cumulative return) achieves 15.03% (1170.42%), which is better than the method of Lee et al. 13.88% (947.65%), and the buy-and-hold strategy 9.85% (442.90%).
目次 Table of Contents
THESIS VERIFICATION FORM . . . . . . . . . . . . . . . . . . . . . . i
THESIS AUTHORIZATION FORM . . . . . . . . . . . . . . . . . . . . iii
ACKNOWLEDGMENTS . . . . . . . . . . . . . . . . . . . . . . . . . . . iv
CHINESE ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi
LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ix
LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xii
ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 0
Chapter 1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Chapter 2. Preliminaries . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.1 Gene Expression Programming . . . . . . . . . . . . . . . . . . . . . 3
2.2 Dynamic Time Warping . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.3 Training Trading Strategy of Lee et al. . . . . . . . . . . . . . . . . . 13
2.4 Technical Indicators . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
2.5 Similarity Measurement . . . . . . . . . . . . . . . . . . . . . . . . . 20
2.6 The US Stock Indices . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
Chapter 3. Our Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.2 Date Alignment of Taiwan and US Markets . . . . . . . . . . . . . . 27
3.3 Similarity Computation . . . . . . . . . . . . . . . . . . . . . . . . . . 27
3.4 Weighted Signals Combination . . . . . . . . . . . . . . . . . . . . . . 30
Chapter 4. Experimental Results . . . . . . . . . . . . . . . . . . . . . . 34
4.1 Data Set and Preprocessing . . . . . . . . . . . . . . . . . . . . . . . 34
4.2 Experimental Environment . . . . . . . . . . . . . . . . . . . . . . . . 34
4.3 Simulation Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
4.3.1 Similarity Calculation . . . . . . . . . . . . . . . . . . . . . . 36
4.3.2 Performance Analysis and Comparison . . . . . . . . . . . . . 38
Chapter 5. Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53
BIBLIOGRAPHY . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
Appendixes
A. The Complete Results of Simulation . . . . . . . . . . . . . . . . . . 57
參考文獻 References
[1] "Dow Jones industrial average index in Wiki." https://en.wikipedia.org/wiki/Dow_Jones_Industrial_Average.
[2] "NASDAQ." http://www.nasdaq.com/.
[3] "NASDAQ in Investopedia." http://www.investopedia.com/terms/n/nasdaqcompositeindex.asp.
[4] "NASDAQ in Wiki." https://en.wikipedia.org/wiki/Nasdaq_Composite.
[5] "Standard & Poor's 500." https://en.wikipedia.org/wiki/S&P_500_Index.
[6] "The root-mean-square deviation." https://en.wikipedia.org/wiki/Root-mean-square_deviation.
[7] "Yahoo finance." https://finance.yahoo.com/.
[8] E. S. Ahmad Kazem, F. K. Hussain, M. Saberi, and O. K. Hussain, "Support vector regression with chaos-based firefly algorithm for stock market price forecasting," Applied Soft Computing 13, Vol. 13, pp. 947-958, 2013.
[9] S. K. Aityana, A. K. Ivanov-Schitz, and S. S. Izotov, "Time-shift asymmetric correlation analysis of global stock markets," International Financial Markets, Institutions and Money, Vol. 20, pp. 590-605, 2010.
[10] D. J. Berndt and J. Clifford, "Using dynamic time warping to find patterns in time series," Proc. of Workshop on Knowledge Discovery and Data Mining, Vol. 10, pp. 359-370, Seattle, Washington, USA, 1994.
[11] P. C. Chang, C. Y. Fan, and J. J. Lin, "Integrating a piecewise linear representation method with dynamic time warping system for stock trading decision making," Proc. of Fourth International Conference on Natural Computation, Vol. 2, Jinan, China, pp. 434-438, Oct. 2008.
[12] S. M. Chen, H. P. Chu, and T. W. Sheu, "Taiex forecasting using fuzzy time series and automatically generated weights of multiple factors," IEEE Transactions on Systems, Man, and Cybernetics part A: Systems and Humans, Vol. 42, No. 6, pp. 1485-1494, 2012.
[13] C. Y. Chou, C. B. Yang, and H. H. Chen, "Portfolio investment based on gene expression programming," Proc. of the 32nd International Conference on Computers and Their Applications, Honolulu, Hawaii, USA, pp. 225-230, Mar. 2017.
[14] J. Corn field, "A method of estimating comparative rates from clinical data. applications to cancer of the lung, breast, and cervix," Journal of the National Cancer Institute, Vol. 11, No. 6, pp. 1269-1275, 1951.
[15] A. W. Edwards, "The measure of association in a 2∗2 table," Journal of the Royal Statistical Society. Series A (General), pp. 109-114, 1963.
[16] C. Ferreira, "Gene expression programming: A new adaptive algorithm for solving problems," Complex Systems, Vol. 13, pp. 87-129, 2001.
[17] C. M. Hsu, "A hybrid precedure for stock price prediction by integrating self-organizing map and genetic programming," Expert Systems with Applications, Vol. 38, pp. 14026-14036, 2011.
[18] C. F. Huang, "A hybrid stock selection model using genetic algorithms and support vector regression," Applied Soft Computing, Vol. 12, pp. 807-818, 2012.
[19] 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, No. 1, pp. 65-75, 2012.
[20] S. M. Jhou, C. B. Yang, and H. H. Chen, "Taiwan stock forecasting with the genetic programming," Proc. of the 16th Conference on Arti ficial Intelligence and Application (Domestic Track), Chungli, Taiwan, pp. 151-157, Nov. 2011.
[21] J. R. Koza, Genetic Programming: On the programming of computers by means of natural selection, Vol. 1. Cambridge, USA, MA: MIT press, 1992.
[22] C. H. Lee, C. B. Yang, and H. H. Chen, "Taiwan stock investment with gene expression programming," Procedia Computer Science, Vol. 35, pp. 137-146, 2014.
[23] F. Mosteller, "Association and estimation in contingency tables," Journal of the American Statistical Association, Vol. 63, No. 321, pp. 1-28, 1968.
[24] L. P. Ni, Z. W. Ni, and Y. Z. Gao, "Stock trend prediction based on fractal feature selection and support vector machine," Expert Systems with Applications, Vol. 38, pp. 5569-5576, 2011.
[25] Ryan J. O'Neil, "Gene Expression Programming for Python." https://code.google.com/p/pygep/, 2007.
[26] Taiwan Economic Journal Co., Ltd, "TEJ." http://www.tej.com.tw/twsite/, 1991.
[27] T. J. Tsai, C. B. Yang, and Y. H. Peng, "Genetic algorithms for the investment of the mutual fund with global trend indicator," Expert Systems with Applications, Vol. 38(3), pp. 1697-1701, 2011.
[28] T. L. Wang and M. Wang, "Features extraction based on particle swarm optimization for high frequency fi nancial data," Proc. of IEEE International Conference on Granular Computing (GrC), Kaohsiung, Taiwan, pp. 728-733, Nov. 2011.
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code