跳到主要內容

臺灣博碩士論文加值系統

(44.200.171.156) 您好!臺灣時間:2023/03/22 02:33
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:何至軒
研究生(外文):HO, CHIH-HSUAN
論文名稱:遺傳演算法應用於台股與美國存託憑證之研究
論文名稱(外文):A Study of Pairs Trading Strategy in Taiwan Equities Market and ADR Using Genetic Algorithms
指導教授:黃健峯
指導教授(外文):Huang, Chien-Feng
口試委員:陳志忠張志向黃健峯
口試委員(外文):CHEN, CHI-CHUNGCHANG, CHIH-HSIANGHUANG, CHIEN-FENG
口試日期:2022-08-25
學位類別:碩士
校院名稱:國立高雄大學
系所名稱:資訊工程學系碩士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:66
中文關鍵詞:配對交易美國存託憑證遺傳演算法統計套利
外文關鍵詞:pair tradingADRgenetic algorithmsarbitrage
相關次數:
  • 被引用被引用:1
  • 點閱點閱:71
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
本研究採用遺傳演算法應用於配對交易策略,使用台股5家公司及其在美國發行之美國存託憑證(American Depositary Receipts, ADR)來作為互相配對商品,由於台股及美股市場交易時間未重合,本文提出兩種可應用於實際交易之配對方法,(一)台股收盤價與當晚美股ADR開盤價配對 (二)美股ADR收盤價與隔日台股開盤價配對,交易條件為前一交易日報酬率作為布林通道,實驗期間為2000年1月1日至2020年12月31日20年,共計21年。結果證實兩種配對方法應用於台股5 家公司皆有不同程度的獲利,說明美國存託憑證與普通股之間有波動報酬外溢現象,且兩者跨不同時區市場交易仍存在套利空間,另本文提出可自動判斷兩種配對方法孰優之演算法加入至新交易模型,實驗結果證實新模型可更廣泛應用於不同類型股票上,在測試期的績效報酬也比僅使用單一種配對方法來得穩定,且風險較長期持有策略來得低。
The study employs genetic algorithms (GA) for the construction of pairs trading models across different trading time zones. Using 5 listed stocks in Taiwan and its American Depositary Receipts (ADR), we propose 2 pairing methods for trading between Taiwan and US stock market: (1) Using the closing price of Taiwan equity and the opening price of ADR for pairs trading; (2) using the closing price of ADR and the opening price of Taiwan equity for pairs trading. The results show that the 2 models of pairs trading have varying degrees of profits, thereby indicating the spillover phenomenon of return and volatility between ADR and Taiwan common stocks. In addition, both of them with different time zones still have arbitrage opportunity in trading. Furthermore, we propose the third kind of pairing methods that can evolve automatically to generate a better model than the previous two ones. The results show that the performance of the third model is more stable than using single pairing method and the risk is lower than the buy and hold strategy.
中文摘要 i
誌謝 iv
目錄 v
表目錄 viii
圖目錄 ix
1. 導論 1
1.1 研究背景 1
1.2 研究目的 1
1.3 論文架構 2
2. 文獻探討 3
2.1 統計套利相關文獻 3
2.2 美國存託憑證ADR 3
2.3 人工智慧及金融科技 5
3. 研究方法 7
3.1 選股及資料來源 7
3.2 交易模型 8
3.3 技術指標 9
3.3.1 移動平均線(MA) 9
3.3.2 布林通道 9
3.4 績效指標 11
3.4.1 總報酬率計算 11
3.4.2 年化收益率(return) 12
3.4.3 最大下跌幅度(maximum drawdown) 12
3.4.4 克馬比率Calmar ratio 12
3.4.5 資訊比率Information ratio 13
3.5 遺傳演算法 13
3.5.1 基因編碼方式 13
3.5.2 親代選擇、交配及突變機制 14
3.5.3 演化流程 15
3.5.4 實驗流程 16
4. 研究結果 18
4.1 Benchmark 18
4.2 驗證研究方式:Temporal Validation 18
4.3 研究結果比較 19
4.3.1 報酬比較 19
4.3.2 加入M3方法比較 30
4.3.3 加入Information Ratio風險指標報酬比較 40
4.3.4 加入Calmar Ratio風險指標報酬比較 44
4.3.5 Maximum drawdown風險指標比較 47
5. 結論 52
參考文獻 53

[1]H. S. Shin, "Risk and liquidity in a system context," Journal of Financial Intermediation, vol. 17, no. 3, pp. 315-329, 2008.
[2]C. S. Asness, A. Frazzini, and L. H. Pedersen, "Leverage aversion and risk parity," Financial Analysts Journal, vol. 68, no. 1, pp. 47-59, 2012.
[3]A. Schrimpf, H. S. Shin, and V. Sushko, "Leverage and margin spirals in fixed income markets during the Covid-19 crisis,", 2020.
[4]G. Vidyamurthy, Pairs Trading: quantitative methods and analysis. John Wiley & Sons, 2004.
[5]C. Alexander and A. Dimitriu, "The cointegration alpha: Enhanced index tracking and long-short equity market neutral strategies," ISMA Finance Discussion Paper, No. 2002-08, 2002.
[6]E. Gatev, W. N. Goetzmann, and K. G. Rouwenhorst, "Pairs trading: Performance of a relative-value arbitrage rule," The Review of Financial Studies, vol. 19, no. 3, pp. 797-827, 2006.
[7]盧冠言, "配對交易是否仍可於當今市場上獲取超額報酬?─以台灣股票市場為例," 碩士論文,財務金融學研究所, 國立臺灣大學, 2020.
[8]張世潔, "美股-臺股股價報酬之共移性及海外存託憑證與臺灣原股之報酬波動外移溢效果," 碩士論文, 國際企業學研究所, 國立臺灣大學,2000.
[9]吳昭勳, "美國存託憑證報酬與風險傳遞之研究," 碩士論文, 財務金融學系, 國立中央大學, 2002.
[10]黃淑吟, "台積電發行美國存託憑證之研究," 碩士論文, 國際企業研究所, 國立成功大學, 1998.
[11]E. F. Fama, "Efficient capital markets: A review of theory and empirical work," The journal of Finance, vol. 25, no. 2, pp. 383-417, 1970.
[12]G. Hong and R. Susmel, "Pairs-trading in the Asian ADR market," University of Houston, Unpublished Manuscript, 2003.
[13]辛依霖, "ADR折溢價因素探討-以大中華地區為例," 碩士論文, 財務金融學研究所, 國立臺灣大學, 2012.
[14]李雯華, "美國存託憑證與相關變數之互動研究及其套利策略," 碩士論文, 財務金融學系, 淡江大學,2001.
[15]A. F. Perold and W. F. Sharpe, "Dynamic strategies for asset allocation," Financial Analysts Journal, vol. 44, no. 1, pp. 16-27, 1988.
[16]李俊明, "美國存託憑證與普通股間之互動關係--以台灣電子業為例," 碩士論文, 國際企業管理研究所, 中國文化大學, " 2001.
[17]魏世傑, "市場價格與波動傳遞效果-以臺灣ADR為例," 碩士論文, 財務金融研究所碩士班, 國立臺中科技大學, 2018.
[18]劉恒瑄, "配對交易於台灣股票與美國存託憑證之實證研究," 碩士論文, 統計學系, 國立臺北大學, 2021.
[19]X. Fu and A. Patra, "Machine Learning in Statistical Arbitrage," Retrieved June, vol. 2, p. 2017, 2009.
[20]P. Saks and D. Maringer, "Genetic programming in statistical arbitrage," in Workshops on Applications of Evolutionary Computation, 2008: Springer, pp. 73-82.
[21]L. A. Becker and M. Seshadri, "GP-evolved technical trading rules can outperform buy and hold," in 3rd international workshop on computational intelligence in economics and finance, 2003.
[22]C.-F. Huang, T.-N. Hsieh, B. R. Chang, and C.-H. Chang, "A comparative study of stock scoring using regression and genetic-based linear models," in 2011 IEEE International Conference on Granular Computing, pp. 268-273.
[23]N. S. Thomaidis, N. Kondakis, and G. D. Dounias, "An intelligent statistical arbitrage trading system," in Hellenic Conference on Artificial Intelligence, 2006: Springer, pp. 596-599.
[24]蔡銘蔚, "一個植基於長短期記憶神經網路之 選股模型的研究," 碩士論文, 資訊工程學系碩士班, 國立高雄大學, 2020.
[25]劉凱騏, "虛擬貨幣之避險績效–以比特幣、乙太幣及萊特幣為例," 碩士論文, 資訊管理學系, 東吳大學,2020.
[26]C.-F. Huang, C.-J. Hsu, C.-C. Chen, B. R. Chang, and C.-A. Li, "An intelligent model for pairs trading using genetic algorithms," Computational Intelligence and Neuroscience, vol. 2015, 2015.
[27]許良宇, "一個使用遺傳演算法在統計套利模型之研究," 碩士論文, 資訊工程學系碩士班, 國立高雄大學, 2017.
[28]C.-H. Chen, W.-H. Lai, S.-T. Hung, and T.-P. Hong, "An Advanced Optimization Approach for Long-Short Pairs Trading Strategy Based on Correlation Coefficients and Bollinger Bands," Applied Sciences, vol. 12, no. 3, p. 1052, 2022.
[29]E. Acar and S. James, "Maximum loss and maximum drawdown in financial markets," in Proceedings of International Conference on Forecasting Financial Markets, 1997.
[30]T. W. Young, "Calmar ratio: A smoother tool," Futures, vol. 20, no. 1, p. 40, 1991.
[31]T. H. Goodwin, "The information ratio," Financial Analysts Journal, vol. 54, no. 4, pp. 34-43, 1998.
[32]J. H. Holland, Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. MIT press, 1992.
[33]D. E. Goldberg and K. Deb, "A comparative analysis of selection schemes used in genetic algorithms," in Foundations of genetic algorithms, vol. 1: Elsevier, pp. 69-93, 1991.
[34]K. A. De Jong, W. M. Spears, and D. F. Gordon, "Using genetic algorithms for concept learning," Machine learning, vol. 13, no. 2, pp. 161-188, 1993.
[35]C.-F. Huang, "A hybrid stock selection model using genetic algorithms and support vector regression," Applied Soft Computing, vol. 12, no. 2, pp. 807-818, 2012.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊