簡易檢索 / 詳目顯示

回結果列表
研究生： 曾業程
Chan Yeh Chern
論文名稱： 短期配對交易策略與時間序列分類的運用
Short-Term Trading in Pairs Trading Strategy Using Time Series Classification
指導教授： 呂永和
Yungho Leu
口試委員: 楊維寧
Wei-Ning Yang
陳雲岫
Yun-Shiow Chen
學位類別： 碩士
Master
系所名稱： 管理學院 - 資訊管理系
Department of Information Management
論文出版年： 2023
畢業學年度： 112
語文別： 英文
論文頁數： 50
外文關鍵詞： Pairs Trading, Short-Term Trading, Time Series Classification
相關次數： 點閱：77  下載：5 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  •  上一筆

    • This study explores pairs trading strategies within the Technology and Industrial sectors, emphasizing the impact of stock pairings that cointegrate with the S&P 500, stock pairings that do not cointegrate with the S&P 500, and predictive modeling on trading outcomes. The analysis showed that in the Technology sector, pairings involving stocks cointegrated with the S&P 500 show marginally higher profitability compared to non-cointegrated pairings, though the difference is minimal and barely noticeable. In the Industrial sector, pairs cointegrated with the S&P 500 consistently yield higher average annualized ROI, largely due to a greater number of trades facilitated by their faster mean-reverting properties. Moreover, the trading simulation using a predictive short-term strategy, based on LSTM modeling for classifying spread movements, shows a generally positive annualized ROI across most pairs. However, certain pairings exhibit negative returns or low profitability, which can be linked to the lower accuracy in predicting spread classifications. Overall, while the short-term strategy demonstrates a lower annualized ROI compared to a conventional pairs trading benchmark, it presents unique opportunities only achievable through predictive modeling. Specifically, in cases where traditional pairs trading fails to yield profit due to prolonged holding periods or lack of mean reversion, the predictive short-term strategy shows potential advantages, suggesting its viability as a supplementary approach to conventional pairs trading methods.

    ACKNOWLEDGEMENT i ABSTRACT ii LIST OF FIGURES iii LIST OF TABLES iii Chapter 1 Introduction 1 1.1 Pairs Trading Strategy 1 1.2 Research Questions 4 1.2.1 Pairs Trading With Double Cointegration Approach 4 1.2.2 Short-Term Pairs Trading Strategies 5 1.2.3 Applications of Deep Learning Model 5 Chapter 2 Literature Review 6 2.1 Pre-Selection Procedures (Before Pairing) 6 2.2 Pairs Selection 7 2.3 Pairs Trading Strategy 8 2.4 Applications of Deep Learning in Pairs Trading 9 Chapter 3 Methodology 10 3.1 Data Collection and Description 10 3.2 Research Method and Design 10 3.2.1 Stock Pairing Stage 1: Pre-Selection Stage 11 3.2.2 Stock Pairing Stage 2: Cointegration Test 12 3.2.3 Stock Pairing Stage 3: Hurst Exponent 13 3.2.4 Trading Strategy : First Research Objective 15 3.2.5 Trading Strategy : Second Research Objective 16 3.3 LSTM 17 3.4 Data Preprocessing 18 3.4.1 Data Transformation 18 3.4.2 Data Annotation/Labeling 22 3.4.3 Data Cleaning, Scaling, and Preparation 22 3.5 LSTM Model 23 3.6 Evaluation Metrics 24 Chapter 4 Results and Discussion 26 4.1 Stock Selection 26 4.2 Cointegration Test 28 4.2.1 Pairing Among Stocks Cointegrated With S&P 500 28 4.2.2 Pairing Among Stocks Not Cointegrated With S&P 500 31 4.2.3 Cointegration Test Discussion 32 4.3 Hurst Exponent 32 4.3.1 Hurst Exponent for Pairings Cointegrated With S&P 500 33 4.3.2 Hurst Exponent for Pairings Not Cointegrated With S&P 500 33 4.4 Trading Performance 34 4.4.1 Trading Performance for Pairings Cointegrated With S&P500 34 4.4.2 Trading Performance for Pairings Not Cointegrated With S&P 500 35 4.4.3 Discussion on Trading Performance 36 4.5 Evaluation of Prediction Model 38 4.5.1 Evaluation for Pairings Cointegrated With S&P 500 38 4.5.2 Evaluation for Pairings Not Cointegrated With S&P 500 40 4.6 Trading Performance of Short-Term Strategy 41 4.6.1 Trading Performance for Pairings Cointegrated With S&P 500 41 4.6.2 Trading Performance for Pairings Not Cointegrated With S&P500 43 4.6.3 Discussion 43 4.7 Limitations of Research 44 4.8 Future Research 45 Chapter 5 Conclusion 46 References 48

    [1] Ramos-Requena, J. P., López-García, M. N., Sánchez-Granero, M. A., & Trinidad-Segovia, J. E. (2021, October 13). A Cooperative Dynamic Approach to Pairs Trading. Complexity, 2021, 1–8. https://doi.org/10.1155/2021/7152846
    [2] Riedinger, S. S. (2017). Demystifying Pairs Trading: The Role of Volatility and Correlation. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2774063
    [3] Chang, V., Man, X., Xu, Q., & Hsu, C. (2020, November 18). Pairs trading on different portfolios based on machine learning. Expert Systems, 38(3). https://doi.org/10.1111/exsy.12649
    [4] Caldeira, J., & Moura, G. V. (2013). Selection of a Portfolio of Pairs Based on Cointegration: A Statistical Arbitrage Strategy. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2196391
    [5] Ramos-Requena, J., Trinidad-Segovia, J., & Sánchez-Granero, M. (2017, December). Introducing Hurst exponent in pair trading. Physica A: Statistical Mechanics and Its Applications, 488, 39–45. https://doi.org/10.1016/j.physa.2017.06.032
    [6] Sarmento, S. M., & Horta, N. (2020, November). Enhancing a Pairs Trading strategy with the application of Machine Learning. Expert Systems With Applications, 158, 113490. https://doi.org/10.1016/j.eswa.2020.113490
    [7] Gatev, E., Goetzmann, W. N., & Rouwenhorst, K. G. (2006). Pairs Trading: Performance of a Relative-Value Arbitrage Rule. Review of Financial Studies, 19(3), 797–827. https://doi.org/10.1093/rfs/hhj020
    [8] Ramos-Requena, J. P., Trinidad-Segovia, J. E., & Sánchez-Granero, M. N. (2020, March 5). Some Notes on the Formation of a Pair in Pairs Trading. Mathematics, 8(3), 348. https://doi.org/10.3390/math8030348
    [9] Flori, A., & Regoli, D. (2021, December). Revealing Pairs-trading opportunities with long short-term memory networks. European Journal of Operational Research, 295(2), 772–791. https://doi.org/10.1016/j.ejor.2021.03.009
    [10] Cavalcanti, R. S. G., Santos, J. F. D., Santos, R. R. D., & Cunha, A. G. M. D. (2021, August). Composition of portfolios by pairs trading with volatility criteria in the Brazilian market,. Revista Contabilidade & Finanças, 32(86), 273–284. https://doi.org/10.1590/1808-057x202110890
    [11] Han, C., He, Z., & Toh, A. J. W. (2023, June). Pairs trading via unsupervised learning. European Journal of Operational Research, 307(2), 929–947. https://doi.org/10.1016/j.ejor.2022.09.041
    [12] Smith, R. T., & Xu, X. (2017, February). A good pair: alternative pairs-trading strategies. Financial Markets and Portfolio Management, 31(1), 1–26. https://doi.org/10.1007/s11408-016-0280-x
    [13] Miao, G. J. (2014, February 24). High Frequency and Dynamic Pairs Trading Based on Statistical Arbitrage Using a Two-Stage Correlation and Cointegration Approach. International Journal of Economics and Finance, 6(3). https://doi.org/10.5539/ijef.v6n3p96
    [14] Zhang, L. (2021, May 28). Pair Trading with Machine Learning Strategy in China Stock Market. 2021 2nd International Conference on Artificial Intelligence and Information Systems. https://doi.org/10.1145/3469213.3471353
    [15] Ghosh, Indranil and Chaudhuri, Tamal and Singh, Priyam (April 10, 2018). Application of Machine Learning Tools in Predictive Modeling of Pairs Trade in Indian Stock Market. The IUP Journal of Applied Finance, Vol. 23, No. 1, January 2017, pp. 5-25. https://ssrn.com/abstract=3159868
    [16] Perry J. Kaufmann (March 8, 2011). Alpha Trading: Profitable Strategies That Remove Directional Risk. Wiley; 1 edition
    [17] Chainika Thakar (July 25, 2022). Augmented Dickey Fuller (ADF) Test for a Pairs Trading Strategy. Quantitative Finance & Algo Trading Blog by QuantInsti. https://blog.quantinsti.com/augmented-dickey-fuller-adf-test-for-a-pairs-trading-strategy/
    [18] Vibhu Singh, Varun Divakar, Ashish Garg (October 29, 2018). Hurst Exponent: Calculation, Values and More. Quantitative Finance & Algo Trading Blog by QuantInsti. https://blog.quantinsti.com/hurst-exponent/
    [19] MACD (Moving Average Convergence/Divergence Oscillator) [ChartSchool]. (n.d.). https://school.stockcharts.com/doku.php?id=technical_indicators:moving_average_convergence_divergence_macd
    [20] Moving Averages - Simple and Exponential [ChartSchool]. (n.d.). https://school.stockcharts.com/doku.php?id=technical_indicators:moving_averages
    [21] Stochastic Oscillator for Technical Analysis: How to Use and Read | FBS. (n.d.). FBS. https://fbs.com/analytics/guidebooks/stochastic-49
    [22] Long Short-Term Memory (LSTM) — Dive into Deep Learning 1.0.3 documentation. (n.d.). https://d2l.ai/chapter_recurrent-modern/lstm.html

    QR CODE