學術產出-Theses
Article View/Open
Publication Export
-
題名 Black-Litterman 模型結合強化學習之投資組合配置
Black-Litterman Portfolios with Reinforcement Learning Derived View作者 李雍群
Li, Yung-Chun貢獻者 廖四郎
Liao, Szu-Lang
李雍群
Li,Yung-Chun關鍵詞 投資組合
強化學習
Black-Litterman模型
近端策略優化
Portfolio
Reinforcement Learning
Black-Litterman Model
Proximal Policy Optimization日期 2022 上傳時間 1-Aug-2022 17:30:18 (UTC+8) 摘要 本研究嘗試將強化學習 (Reinforcement Learning) 應用於預測金融資產價格走勢，並結合Black-Litterman模型建構全球性多元投資組合。本研究使用近端策略優化演算法 (Proximal Policy Optimization, PPO)，以資產價量資料預測資產價格漲跌及漲跌幅度，並將預測結果作為Black-Litterman模型中的投資者觀點進行資產配置，比較投資組合在不同獎勵設定及不同更新次數下的績效表現。本研究以美國五檔不同資產類別ETF作為基礎資產，研究結果顯示強化學習在一定更新次數上具有預測力，本研究建立之投資組合績效在更新次數600000皆能贏過其餘基準模型。另外，對於強化學習而言，以不同獎勵設定訓練模型比起增加更新次數對績效有著較大的影響。
In this thesis, we try to apply reinforcement learning to forecasting price trends of finance assets. We combine the forecasts with the Black-litterman model and construct various globally diversified portfolios. In our paper, we use the Proximal Policy Optimization algorithm to forecast assets’ price trends by historical price and volume. The prediction of results are used as the investor’s views in the Black-Litterman model for asset allocation. This study compares the performance of the portfolios under different reward setting and number of updates. The empirical results show that reinforcement learning has predictive power at a certain number of updates. The portfolios performance in this study outperform the benchmark portfolios at 600,000 updates. In addition, for the reinforcement learning, training the model with different reward setting has a greater impact on performance than increasing the number of updates.參考文獻 [1] Black, F., & Litterman, R. (1991), “Asset Allocation: Combining Investor Views with Market Equilibrium.” The Journal of Fixed Income, 1(2), 7-18.[2] Black, F., & Litterman, R. (1992), “Global Portfolio Optimization.” Financial Analysts Journal, 48(5), 28-43.[3] Black, F., Jensen, M. C., & Scholes, M. (1972), “The Capital Asset Pricing Model: Some Empirical Tests.” In M. Jenson, ed., Studies in the Theory of Capital Markets (Praeger, New York, NY).[4] Donthireddy, P. (2018), “Black-Litterman Portfolios with Machine Learning derived Views.” ResearchGate. Retired April 12, 2022, from https://www.researchgate.net/publication/326489143_Black-Litterman_Portfolios_with_Machine_Learning_derived_Views[5] He, G., & Litterman, R. (2002), “The intuition behind Black-Litterman model portfolios.” Available at SSRN 334304.[6] Jiang, Z., & Liang, J. (2017, September), “Cryptocurrency Portfolio Management with Deep Reinforcement Learning.” In 2017 Intelligent Systems Conference (IntelliSys), 905-913, IEEE.[7] Lin, E., Chen, Q., & Qi, X. (2020), “Deep reinforcement learning for imbalanced classification.” Applied Intelligence, 50(8), 2488-2502.[8] Lintner, J. (1965), “Security Prices, Risk, and Maximal Gains from Diversification.” The Journal of Finance, 20(4), 587-615.[9] Markowitz, H.(1952), “Portfolio selection.” The Journal of Finance,7(1),77-91[10] Meucci, A. (2010), “The Black-Litterman Approach: Original Model and Extensions.” Shorter version in, The Encyclopedia Of Quantitative Finance, Wiley.[11] Moody, J., & Saffell, M. (2001), “Learning to Trade Via Direct Reinforcement.” IEEE transactions on neural Networks, 12(4), 875-889.[12] Neuneier, R. (1997), “Enhancing Q-Learning For Optimal Asset Allocation.” Advances In Neural Information Processing Systems, 10. 936-942[13] Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017), “Proximal Policy Optimization Algorithms.” arXiv:1707.06347[14] Sharpe, W. F. (1964), “Capital Asset Prices: A Theory of Market Equilibrium under Conditions of Risk.” The journal of finance, 19(3), 425-442.[15] Treynor, J. L. (1961), “Market Value, Time, and Risk.” Available at SSRN 2600356.[16] Zhang, Y., Zhao, P., Li, B., Wu, Q., Huang, J., & Tan, M. (2020), “Cost-Sensitive Portfolio Selection Via Deep Reinforcement Learning.” IEEE Transactions on Knowledge and Data Engineering 描述 碩士
國立政治大學
金融學系
109352028資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109352028 資料類型 thesis dc.contributor.advisor 廖四郎 zh_TW dc.contributor.advisor Liao, Szu-Lang en_US dc.contributor.author (Authors) 李雍群 zh_TW dc.contributor.author (Authors) Li,Yung-Chun en_US dc.creator (作者) 李雍群 zh_TW dc.creator (作者) Li, Yung-Chun en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-Aug-2022 17:30:18 (UTC+8) - dc.date.available 1-Aug-2022 17:30:18 (UTC+8) - dc.date.issued (上傳時間) 1-Aug-2022 17:30:18 (UTC+8) - dc.identifier (Other Identifiers) G0109352028 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/141067 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 金融學系 zh_TW dc.description (描述) 109352028 zh_TW dc.description.abstract (摘要) 本研究嘗試將強化學習 (Reinforcement Learning) 應用於預測金融資產價格走勢，並結合Black-Litterman模型建構全球性多元投資組合。本研究使用近端策略優化演算法 (Proximal Policy Optimization, PPO)，以資產價量資料預測資產價格漲跌及漲跌幅度，並將預測結果作為Black-Litterman模型中的投資者觀點進行資產配置，比較投資組合在不同獎勵設定及不同更新次數下的績效表現。本研究以美國五檔不同資產類別ETF作為基礎資產，研究結果顯示強化學習在一定更新次數上具有預測力，本研究建立之投資組合績效在更新次數600000皆能贏過其餘基準模型。另外，對於強化學習而言，以不同獎勵設定訓練模型比起增加更新次數對績效有著較大的影響。 zh_TW dc.description.abstract (摘要) In this thesis, we try to apply reinforcement learning to forecasting price trends of finance assets. We combine the forecasts with the Black-litterman model and construct various globally diversified portfolios. In our paper, we use the Proximal Policy Optimization algorithm to forecast assets’ price trends by historical price and volume. The prediction of results are used as the investor’s views in the Black-Litterman model for asset allocation. This study compares the performance of the portfolios under different reward setting and number of updates. The empirical results show that reinforcement learning has predictive power at a certain number of updates. The portfolios performance in this study outperform the benchmark portfolios at 600,000 updates. In addition, for the reinforcement learning, training the model with different reward setting has a greater impact on performance than increasing the number of updates. en_US dc.description.tableofcontents 第一章 緒論 4第一節 研究背景與動機 4第二節 研究目的 5第二章 文獻回顧 6第一節 投資組合理論 6第二節 強化學習之投資領域應用 6第三章 研究方法 8第一節 Black-Litterman 模型 8第二節 強化學習 11第三節 投資策略 18第四章 實證分析 19第一節 資料來源與前處理 19第二節 強化學習之應用 20第三節 實證結果 26第五章 結論與建議 32第一節 結論 32第二節 未來展望 32參考文獻 33 zh_TW dc.format.extent 1715427 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109352028 en_US dc.subject (關鍵詞) 投資組合 zh_TW dc.subject (關鍵詞) 強化學習 zh_TW dc.subject (關鍵詞) Black-Litterman模型 zh_TW dc.subject (關鍵詞) 近端策略優化 zh_TW dc.subject (關鍵詞) Portfolio en_US dc.subject (關鍵詞) Reinforcement Learning en_US dc.subject (關鍵詞) Black-Litterman Model en_US dc.subject (關鍵詞) Proximal Policy Optimization en_US dc.title (題名) Black-Litterman 模型結合強化學習之投資組合配置 zh_TW dc.title (題名) Black-Litterman Portfolios with Reinforcement Learning Derived View en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] Black, F., & Litterman, R. (1991), “Asset Allocation: Combining Investor Views with Market Equilibrium.” The Journal of Fixed Income, 1(2), 7-18.[2] Black, F., & Litterman, R. (1992), “Global Portfolio Optimization.” Financial Analysts Journal, 48(5), 28-43.[3] Black, F., Jensen, M. C., & Scholes, M. (1972), “The Capital Asset Pricing Model: Some Empirical Tests.” In M. Jenson, ed., Studies in the Theory of Capital Markets (Praeger, New York, NY).[4] Donthireddy, P. (2018), “Black-Litterman Portfolios with Machine Learning derived Views.” ResearchGate. Retired April 12, 2022, from https://www.researchgate.net/publication/326489143_Black-Litterman_Portfolios_with_Machine_Learning_derived_Views[5] He, G., & Litterman, R. (2002), “The intuition behind Black-Litterman model portfolios.” Available at SSRN 334304.[6] Jiang, Z., & Liang, J. (2017, September), “Cryptocurrency Portfolio Management with Deep Reinforcement Learning.” In 2017 Intelligent Systems Conference (IntelliSys), 905-913, IEEE.[7] Lin, E., Chen, Q., & Qi, X. (2020), “Deep reinforcement learning for imbalanced classification.” Applied Intelligence, 50(8), 2488-2502.[8] Lintner, J. (1965), “Security Prices, Risk, and Maximal Gains from Diversification.” The Journal of Finance, 20(4), 587-615.[9] Markowitz, H.(1952), “Portfolio selection.” The Journal of Finance,7(1),77-91[10] Meucci, A. (2010), “The Black-Litterman Approach: Original Model and Extensions.” Shorter version in, The Encyclopedia Of Quantitative Finance, Wiley.[11] Moody, J., & Saffell, M. (2001), “Learning to Trade Via Direct Reinforcement.” IEEE transactions on neural Networks, 12(4), 875-889.[12] Neuneier, R. (1997), “Enhancing Q-Learning For Optimal Asset Allocation.” Advances In Neural Information Processing Systems, 10. 936-942[13] Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017), “Proximal Policy Optimization Algorithms.” arXiv:1707.06347[14] Sharpe, W. F. (1964), “Capital Asset Prices: A Theory of Market Equilibrium under Conditions of Risk.” The journal of finance, 19(3), 425-442.[15] Treynor, J. L. (1961), “Market Value, Time, and Risk.” Available at SSRN 2600356.[16] Zhang, Y., Zhao, P., Li, B., Wu, Q., Huang, J., & Tan, M. (2020), “Cost-Sensitive Portfolio Selection Via Deep Reinforcement Learning.” IEEE Transactions on Knowledge and Data Engineering zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200681 en_US
