學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 機器學習方法建構股票市場投資策略及波動度管理
Constructing Stock Risk Portfolios with Volatility Control Using Machine Learning作者 許茱媛
Hsu, Jhu-Yuan貢獻者 黃泓智
許茱媛
Hsu, Jhu-Yuan關鍵詞 機器學習
ETF
波動度控制
Machine Learning
ETF
Volatility Control日期 2023 上傳時間 1-九月-2023 16:06:25 (UTC+8) 摘要 本研究以台灣股票市場作為研究標的，納入每季的財報資料和常用技術指標進行集成學習，集成學習模型包含XGBoost、MLP和SVR進行投票法，選用不同類型的模型期望能提升單一模型績效，以更好的預測股票波動，進而建立最適投資組合，觀察合適的投資組合方法與檔數，挑選股票類投資策略和ETF投資策略進行後續的波動度管理。本文採用低波動之ETF標的建立不同風險投資人的投資策略，搭配目標波動度方法進行波動控制，並使用不同指標，包含日報酬、最大回落、VIX與LSTM預測隔日報酬做波動度上限指標，同時配合不同門檻值觀察來實證波動度管理之績效。實證結果發現，採用ETF控制波動下的投資策略除了降低波動度外，可以達到更好的夏普比率。
This study focuses on the Taiwan stock market as the research subject, incorporating quarterly financial data and commonly used technical indicators for ensemble learning. The ensemble learning model includes XGBoost, MLP, and SVR using the voting method, with the expectation of improving the performance of individual models to better predict stock volatility. The ultimate goal is to establish an optimal investment portfolio and observe suitable investment methods and the number of holdings. Stock investment strategies and ETF investment strategies will be selected for subsequent volatility control.In this paper, low-volatility ETFs are used to establish investment strategies for different risk-tolerant investors. Target volatility methods are applied for volatility control, and various indicators, including daily returns, maximum drawdown, VIX, and LSTM prediction, are used as volatility upper bound indicators. Different threshold values are used to empirically test the performance of volatility management. Empirical results indicate that employing ETFs for volatility control in investment strategies not only reduces volatility but also leads to better Sharpe ratios.參考文獻 林晏緯（2021）。利用集成學習建構股市最適投資組合。〔未出版之碩士論文〕。淡政治大學風險管理與保險學系。錢慧娟（2022）。訊號分解對於集成學習預測股價準確率之影響—以台灣加權股價指數為例。〔未出版之碩士論文〕。淡政治大學風險管理與保險學系。Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794).Choudhury, S., Ghosh, S., Bhattacharya, A., Fernandes, K. J., & Tiwari, M. K. (2014). A real-time clustering and SVM based price-volatility prediction for optimal trading strategy. Neurocomputing, 131, 419-426. ISSN 0925-2312. https://doi.org/10.1016/j.neucom.2013.10.002Connell, P., & Hodgson, M. (2016). Managing investment outcomes with volatility control. Schroder Investment Management North America Inc.Hochreiter, Sepp & Schmidhuber, Jürgen. (1997). Long Short-term Memory. Neural computation. 9. 1735-80. 10.1162/neco.1997.9.8.1735.Huang, Y., Capretz, L. F., & Ho, D. (2021). Machine Learning for Stock Prediction Based on Fundamental Analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 01-10). Orlando, FL, USA. https://doi.org/10.1109/SSCI50451.2021.9660134Jiang, W. (2021). Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications, 184, 115537. ISSN 0957-4174. https://doi.org/10.1016/j.eswa.2021.115537.Jidong, L., & Ran, Z. (2018). Dynamic Weighting Multi Factor Stock Selection Strategy Based on XGBoost Machine Learning Algorithm. In 2018 IEEE International Conference of Safety Produce Informatization (IICSPI) (pp. 868-872). Chongqing, China. doi: 10.1109/IICSPI.2018.8690416.Li, Y., & Pan, Y. (2022). A novel ensemble deep learning model for stock prediction based on stock prices and news. International Journal of Data Science and Analysis, 13, 139–149. https://doi.org/10.1007/s41060-021-00279-9Ma, Y., Wang, Y., Wang, W., & Zhang, C. (2023). Portfolios with return and volatility prediction for the energy stock market. Energy, 270, 126958. ISSN 0360-5442. https://doi.org/10.1016/j.energy.2023.126958Maqbool, J., Aggarwal, P., Kaur, R., Mittal, A., & Ganaie, I. A. (2023). Stock Prediction by Integrating Sentiment Scores of Financial News and MLP-Regressor: A Machine Learning Approach. Procedia Computer Science, 218, 1067-1078. ISSN 1877-0509. https://doi.org/10.1016/j.procs.2023.01.086.Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77-91.Mehta, S., Rana, P., Singh, S., Sharma, A., & Agarwal, P. (2019). Ensemble Learning Approach for Enhanced Stock Prediction. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (pp. 1-5). Noida, India. doi: 10.1109/IC3.2019.8844891.Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162-2172. https://doi.org/10.1016/j.eswa.2014.10.031Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.Vapnik, V., & Chervonenkis, A. (1997). Support Vector Regression Machines. In Advances in Neural Information Processing Systems 9 (pp. 281-287).Yun, K. K., Yoon, S. W.&Won, D. (2021). Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, 186, 115716. https://doi.org/10.1016/j.eswa.2021.115716. 描述 碩士
國立政治大學
風險管理與保險學系
110358011資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110358011 資料類型 thesis dc.contributor.advisor 黃泓智 zh_TW dc.contributor.author (作者) 許茱媛 zh_TW dc.contributor.author (作者) Hsu, Jhu-Yuan en_US dc.creator (作者) 許茱媛 zh_TW dc.creator (作者) Hsu, Jhu-Yuan en_US dc.date (日期) 2023 en_US dc.date.accessioned 1-九月-2023 16:06:25 (UTC+8) - dc.date.available 1-九月-2023 16:06:25 (UTC+8) - dc.date.issued (上傳時間) 1-九月-2023 16:06:25 (UTC+8) - dc.identifier (其他 識別碼) G0110358011 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/147206 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 風險管理與保險學系 zh_TW dc.description (描述) 110358011 zh_TW dc.description.abstract (摘要) 本研究以台灣股票市場作為研究標的，納入每季的財報資料和常用技術指標進行集成學習，集成學習模型包含XGBoost、MLP和SVR進行投票法，選用不同類型的模型期望能提升單一模型績效，以更好的預測股票波動，進而建立最適投資組合，觀察合適的投資組合方法與檔數，挑選股票類投資策略和ETF投資策略進行後續的波動度管理。本文採用低波動之ETF標的建立不同風險投資人的投資策略，搭配目標波動度方法進行波動控制，並使用不同指標，包含日報酬、最大回落、VIX與LSTM預測隔日報酬做波動度上限指標，同時配合不同門檻值觀察來實證波動度管理之績效。實證結果發現，採用ETF控制波動下的投資策略除了降低波動度外，可以達到更好的夏普比率。 zh_TW dc.description.abstract (摘要) This study focuses on the Taiwan stock market as the research subject, incorporating quarterly financial data and commonly used technical indicators for ensemble learning. The ensemble learning model includes XGBoost, MLP, and SVR using the voting method, with the expectation of improving the performance of individual models to better predict stock volatility. The ultimate goal is to establish an optimal investment portfolio and observe suitable investment methods and the number of holdings. Stock investment strategies and ETF investment strategies will be selected for subsequent volatility control.In this paper, low-volatility ETFs are used to establish investment strategies for different risk-tolerant investors. Target volatility methods are applied for volatility control, and various indicators, including daily returns, maximum drawdown, VIX, and LSTM prediction, are used as volatility upper bound indicators. Different threshold values are used to empirically test the performance of volatility management. Empirical results indicate that employing ETFs for volatility control in investment strategies not only reduces volatility but also leads to better Sharpe ratios. en_US dc.description.tableofcontents 第一章、 緒論 1第一節、 研究動機 1第二節、 研究架構 2第二章、 文獻回顧 3第一節、 機器學習模型文獻回顧 7第二節、 股價預測文獻回顧 8第三節、 波動度控制文獻回顧 10第三章、 研究方法 12第一節、 特徵選擇及資料預處理 12第二節、 集成學習模型 14第三節、 資產配置方法 19第四節、 波動度管理 19第五節、 投組績效指標 22第四章、 實證結果 24第一節、 資料分析 24第二節、 機器學習結果 26第三節、 集成學習結果 31第四節、 波動度管理 35第五章、 結論與建議 41參考文獻 43 zh_TW dc.format.extent 1750757 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110358011 en_US dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) ETF zh_TW dc.subject (關鍵詞) 波動度控制 zh_TW dc.subject (關鍵詞) Machine Learning en_US dc.subject (關鍵詞) ETF en_US dc.subject (關鍵詞) Volatility Control en_US dc.title (題名) 機器學習方法建構股票市場投資策略及波動度管理 zh_TW dc.title (題名) Constructing Stock Risk Portfolios with Volatility Control Using Machine Learning en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 林晏緯（2021）。利用集成學習建構股市最適投資組合。〔未出版之碩士論文〕。淡政治大學風險管理與保險學系。錢慧娟（2022）。訊號分解對於集成學習預測股價準確率之影響—以台灣加權股價指數為例。〔未出版之碩士論文〕。淡政治大學風險管理與保險學系。Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794).Choudhury, S., Ghosh, S., Bhattacharya, A., Fernandes, K. J., & Tiwari, M. K. (2014). A real-time clustering and SVM based price-volatility prediction for optimal trading strategy. Neurocomputing, 131, 419-426. ISSN 0925-2312. https://doi.org/10.1016/j.neucom.2013.10.002Connell, P., & Hodgson, M. (2016). Managing investment outcomes with volatility control. Schroder Investment Management North America Inc.Hochreiter, Sepp & Schmidhuber, Jürgen. (1997). Long Short-term Memory. Neural computation. 9. 1735-80. 10.1162/neco.1997.9.8.1735.Huang, Y., Capretz, L. F., & Ho, D. (2021). Machine Learning for Stock Prediction Based on Fundamental Analysis. In 2021 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 01-10). Orlando, FL, USA. https://doi.org/10.1109/SSCI50451.2021.9660134Jiang, W. (2021). Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications, 184, 115537. ISSN 0957-4174. https://doi.org/10.1016/j.eswa.2021.115537.Jidong, L., & Ran, Z. (2018). Dynamic Weighting Multi Factor Stock Selection Strategy Based on XGBoost Machine Learning Algorithm. In 2018 IEEE International Conference of Safety Produce Informatization (IICSPI) (pp. 868-872). Chongqing, China. doi: 10.1109/IICSPI.2018.8690416.Li, Y., & Pan, Y. (2022). A novel ensemble deep learning model for stock prediction based on stock prices and news. International Journal of Data Science and Analysis, 13, 139–149. https://doi.org/10.1007/s41060-021-00279-9Ma, Y., Wang, Y., Wang, W., & Zhang, C. (2023). Portfolios with return and volatility prediction for the energy stock market. Energy, 270, 126958. ISSN 0360-5442. https://doi.org/10.1016/j.energy.2023.126958Maqbool, J., Aggarwal, P., Kaur, R., Mittal, A., & Ganaie, I. A. (2023). Stock Prediction by Integrating Sentiment Scores of Financial News and MLP-Regressor: A Machine Learning Approach. Procedia Computer Science, 218, 1067-1078. ISSN 1877-0509. https://doi.org/10.1016/j.procs.2023.01.086.Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77-91.Mehta, S., Rana, P., Singh, S., Sharma, A., & Agarwal, P. (2019). Ensemble Learning Approach for Enhanced Stock Prediction. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (pp. 1-5). Noida, India. doi: 10.1109/IC3.2019.8844891.Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications, 42(4), 2162-2172. https://doi.org/10.1016/j.eswa.2014.10.031Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533-536.Vapnik, V., & Chervonenkis, A. (1997). Support Vector Regression Machines. In Advances in Neural Information Processing Systems 9 (pp. 281-287).Yun, K. K., Yoon, S. W.&Won, D. (2021). Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, 186, 115716. https://doi.org/10.1016/j.eswa.2021.115716. zh_TW
