臺灣博碩士論文加值系統

基於臺灣股法規對當日沖銷的開放以及日內交易撮合資料的公開，本研究希望藉由探討日內交易資料，找尋適當的日內交易策略，為投資人創造超額報酬。本研究假設每個股票基於多空雙方在股價看法上的紛歧而呈現隨機性，但由於投資人的偏好及個股的特性，其每日波動幅度應該與歷史波動幅度有一定的關聯性。因此，本研究透過遺傳演算法，挑選出個股的波動特性，藉此發展個股適用的最佳日內交易策略。希望有效超越傳統長期買入持有的基本投資策略，而能獲取超額報酬。本研究並同時驗證台灣股市與美國股市，在個股日內波動的特性，希望找出一穩定可執行之日內交易策略。
本研究在選股策略方面分別從台灣股市挑選出20個權值股，並於美國股市中挑選道瓊工業指數30個成份股做為研究標的，以比較兩個不同類型股票市場的差異性及驗證本研究策略的可執行性。在資金配置策略上則採取簡單平均的方式，且交易期間資金不流動。研究資料使用2013年6月1日至2014年5月30日之日內交易資料，並用以實驗檢視本研究發展之日內交易之可執行性。本研究透過遺傳演算法搜尋個別股票的波動幅度和移動平均天數的歷史波動相關性，用以找出個股的每日波動特性，藉以預測隔日股票的波動幅度，以預期低點為買點，預期高點為賣點，建立一日內交易策略之模型。本研究並改善遺傳演算法，採用固定突變率時易發生突變率過小時易導致過早收斂到區域最佳解，或突變率過大時導致解答品質穩定性不佳的問題，而發展出變動突變率的方法，使突變率隨著代數遞增而遞減，同時解決落入區域最佳化或穩定性不佳的問題。
研究結果顯示，個股的確可以透過歷史波動幅度預測短期股價的波動幅度，進而找出交易的進出場規則，發展出適合的交易策略，以獲得超越買入持有策略的超額報酬。但日內當沖交易的交易成本過高，若能略微延長持有天數，則可以有效地降低交易成本，提高短期投資效益。

Based on the regulations of Taiwan stocks were opened up day trading and intraday data. This study found the appropriate for intraday trading strategy by intraday data to get excess return for investors. We assumed that each stock had difference price at random on both long and short view. Because investors had different preferences and stocks had different characteristics. Daily volatility and historical volatility should have some relevance. We chose the each stock volatility by genetic algorithms and develop the best stocks intraday trading strategy. Hope to obtain excess return in day trading beyond the long-term buy and hold. In this study, we verified not only the Taiwan stock market but also the United States stock market to find intraday trading strategy of a stable executable.
In the strategies of stock selection, we chose 20 value weignted stocks from Taiwan stock market and 30 DJI’s component stocks. The purpose was to compare two different types of stock market differences and verified that the research strategy of enforceability. We average our capital to each stock. And the capital did not flow during the transaction. Research data used June 1, 2013 to May 30, 2014 the day trading information. In this study, we searched correlation between individual stock volatility and the moving average of historical volatility to find stocks daily fluctuation characteristics through genetic algorithms. In addition to this study also improve the problem that genetic algorithms is unstable.
The results showed the short-term price could be predicted by using historical volatility. We could use the price to trade in stock market and obtain excess returns. When intraday trading’s cost was too high, we could hold a few days to reduce costs

致 謝 I
摘 要 II
Abstract III
目 錄 IV
圖目錄 V
表目錄 VI
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 預期貢獻 3
第四節 論文章節說明 4
第二章 文獻探討 5
第一節 證券投資理論 5
第二節 資料探勘 12
第三節 日內資料 15
第四節 遺傳演算法 17
第三章 研究方法 22
第一節 研究架構與說明 22
第二節 研究工具 28
第四章 實驗說明與結果 29
第一節 實驗一：技術指標有效性驗證 29
第二節 實驗二：當日沖銷交易策略驗證 40
第三節 實驗三：短期持有交易策略驗證 55
第五章 結果與討論 64
第一節 結論與研究貢獻 64
第二節 研究限制 65
第三節 未來研究方向 65
參考文獻 66
附錄一 現股當沖200檔個股標的明細 69

中文文獻
[1] 王朝仕，民100，『投資人對現金增資股票的過度反應行為－魅力性觀點』，管理與系統，第十八卷．第四期：633～662頁。
[2] 杜金龍，民95，最新技術指標－在台灣股市應用的訣竅，台北：財訊出版社。
[3] 侯佳利，民97，以遺傳程式規劃建構靜態及動態非線性投資策略，國立中央大學資訊管理研究所博士論文。
[4] 徐正錦，民92，技術分析應用於台灣股市之實證研究，國立中正大學國際經濟研究所碩士論文。
[5] 陳柏年，民90，應用遺傳演算法於財務指標選股策略之探討，國立中央大學資訊管理研究所碩士論文。
[6] 陳威儒，民99，驗證箱型理論-以台灣股市為例
[7] 張沛翔，民102，超高頻資料變異數估計模型在最適資產配置投資組合上之應用與比較-以臺灣證券市場為例，淡江大學統計學系碩士班碩士論文。
[8] 張麗娟，民98，『散戶投資人後悔情緒與決策行為分析』，中國管理評論國際學報，第十二卷．第一期：1～31頁。
[9] 曾友和，民102，箱形理論與開收盤價差綜合策略應用-以台股期貨TX為例，國立中正大學高階主管管理碩士在職專班碩士論文。
[10] 趙明威，民98，以高頻率日內資料驗證報酬率與波動度之因果關係-以台灣期貨市場為證，國立政治大學金融研究所碩士論文。
[11] 蘇真慧，民101，應用遺傳演算法與關聯規則於股票交易策略之研究，國立東華大學資訊管理碩士學位學程碩士論文。
[12] 臺灣證券交易所，http://www.twse.com.tw/ch/index.php。

英文文獻
[13] Allen, F., and Karjalainen, R. 1999. "Using genetic algorithms to find technical trading rules, " Journal of Financial Economics (51:2), pp 245-271.
[14] Beasley, D., Martin, R. R., and Bull, D. R. 1993. "An overview of genetic algorithms: Part 1. Fundamentals," University computing (15), pp 58-58.
[15] Berry, M. J., and Linoff, G. Data mining techniques: For marketing, sales, and customer support, John Wiley & Sons, Inc., New York, 1997.
[16] Barber, B. M., Lee, Y.-T., Liu, Y.-J., and Odean, T. 2014. "The cross-section of speculator skill: Evidence from day trading," Journal of Financial Markets (18:0), pp 1-24.
[17] De Jong, K. A., and Spears, W. M. 1993. "On the state of evolutionary computation," in Proceedings of the Fifth International Conference on Genetic Algorithms, pp 18-23.
[18] Doeksen, B., Abraham, A., Thomas, J. and Paprzycki, M. 2005. " Real stock trading using soft computing models," Information Technology: Coding and Computing, 2, pp. 162-67.
[19] Darvas, N. How I Made $2 Million in the Stock Market: The Darvas system for stock market profits (September 8, 2011 ed.), BN Publishin, New York, 2011.
[20] Fama, E. F. 1970. "EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK*," The Journal of Finance (25:2), pp 383-417.
[21] Fama, E. F. 1991. "Efficient Capital Markets: II," The Journal of Finance (46:5), pp 1575-1617.
[22] Fayyad, U. M., Piatetsky-Shapiro, G., Smyth, P., and Uthurusamy, R. 1996. Advances in knowledge discovery and data mining. AAAI/MIT Press.
[23] Goldberg, D. E., Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley , Massachusetts, 1989.
[24] Holland, J. H. , Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence, U Michigan Press, 1975.
[25] Kim, S. T., Lin, J.-C., and Slovin, M. B. 1997. "Market structure, informed trading, and analysts’ recommendations," Journal of Financial and Quantitative Analysis (32:4), pp 507-524.
[26] Lo, A. W., and MacKinlay, A. C. A non-Random Walk down Wall Street, Princeton University Press, Princeton, NJ, 1999.
[27] Linnainmaa, J. 2005. "The Individual Day Trader." working paper, UCLA.
[28] Murphy, M. L., and Pichichero, M. E. 2002. "Prospective identification and treatment of children with pediatric autoimmune neuropsychiatric disorder associated with group A streptococcal infection (PANDAS). " Archives of pediatrics & adolescent medicine, 156(4), pp 356-361.
[29] Patell, J. M., and Wolfson, M. A. 1984. "The intraday speed of adjustment of stock prices to earnings and dividend announcements," Journal of Financial Economics (13:2), pp 223-252.
[30] Schwert, G. W., and Seguin, P. J. 1990. "Heteroskedasticity in stock returns," the Journal of Finance (45:4), pp 1129-1155.
[31] Schwert, G. W., and Stambaugh, R. F. 1987. "Expected stock returns and volatility," Journal of Financial Economics (19), pp 3-29.
[32] Wood, R. A., McInish, T. H., and Ord, J. K. 1985. "An investigation of transactions data for NYSE stocks. " The Journal of Finance, 40(3), pp 723-739.
[33] Wen, Q., Yang, Z., Song, Y., and Jia, P. 2010. "Automatic stock decision support system based on box theory and SVM algorithm." Expert Systems with Applications(37), pp 1015-1022