Publications-Theses
Article View/Open
Publication Export
-
題名 隱藏式馬可夫狀態轉換模型下的動態資產配置
Dynamic Asset Allocation under Hidden Markov Regime Switching Model作者 盧建豪
Lu, Chien-Hou貢獻者 江彌修
Chiang, Mi-Hsiu
盧建豪
Lu, Chien-Hou關鍵詞 資產配置
隱藏式馬可夫模型
狀態轉換模型
分層式風險平價
Asset Allocation
Hidden Markov Model
Regime-switching Model
Hierarchical Risk Parity日期 2022 上傳時間 1-Aug-2022 17:30:05 (UTC+8) 摘要 本文探討隱藏式馬可夫狀態轉換模型是否能夠使投資組合績效上升。基於隱藏式馬可夫模型對台灣加權指數進行狀態分類後,得到兩種狀態:高波動低報酬狀態與低波動高報酬狀態。本文建立逆變異數加權、分層式風險評價與二次規劃最小化變異數三個投資組合,並採用 2007 年 1 月 4 日至 2021 年 12 月 31 日的台灣股市資料與美債報酬進行回測。實證發現,狀態轉換下的動態資產配置能使投資組合的夏普比率、索提諾比率與最大策略虧損報酬上升,其中又以加入狀態轉換模型的逆變異數加權投資組合表現最佳。
This paper explores whether a hidden Markov regime-switching model can improve portfolio performance. After we classify the Taiwan Weighted Index based on the Hidden Markov Model, two states are obtained: the state of high volatility and low return, and the state of low volatility and high return. This paper constructs three portfolios: inverse variance weighting, hierarchical risk parity and quadratic programming minimizing variance. We conduct backtests based on Taiwan stock market and U.S. bond data from January 4, 2007 to December 31, 2021. We find thatthe dynamic asset allocation under the regime-switching model can increase the Sharpe ratio, Sortino ratio and maximum drawdown return of the portfolio. The inversevariance weighted portfolio under the regime-switching model performs the best.參考文獻 Ang, A., & Bekaert, G. (2002). International asset allocation with regime shifts. Thereview of financial studies, 15(4), 1137-1187.Bailey, D. H., & Lopez de Prado, M. (2012). The Sharpe ratio efficient frontier. Journalof Risk, 15(2), 13.Bulla, J., Mergner, S., Bulla, I., Sesboüé, A., & Chesneau, C. (2011). Markov-switchingasset allocation: Do profitable strategies exist?. Journal of AssetManagement, 12(5), 310-321.Cajas, D. (2022). Riskfolio-lib (3.0.0). Retrieved fromhttps://github.com/dcajasn/Riskfolio-LibCosta, G., & Kwon, R. (2020). A Regime-Switching Factor Model for Mean-VarianceOptimization. Journal of Risk.De Prado, M. L. (2016). Building diversified portfolios that outperform out ofsample. The Journal of Portfolio Management, 42(4), 59-69.Konstantinov, G., Chorus, A., & Rebmann, J. (2020). A network and machine learningapproach to factor, asset, and blended allocation. The Journal of PortfolioManagement, 46(6), 54-71.Kritzman, M., Page, S., & Turkington, D. (2012). Regime shifts: Implications fordynamic strategies (corrected). Financial Analysts Journal, 68(3), 22-39.Lo, A. W. (2002). The statistics of Sharpe ratios. Financial analysts journal, 58(4), 36-52.Meucci, A. (2009). Managing diversification. Risk, 74-79.Nystrup, P. (2014). Regime-based asset allocation. Do profitable strategiesexist. Master`s thesis, Technical University of Denmark.Nystrup, P., Madsen, H., & Lindström, E. (2017). Long memory of financial time series39and hidden Markov models with time‐varying parameters. Journal ofForecasting, 36(8), 989-1002.Papenbrock, J. (2011). Asset Clusters and Asset Networks in Financial RiskManagement and Portfolio Optimization (Doctoral dissertation, Dissertation,Karlsruhe, Karlsruher Institut für Technologie (KIT), 2011).Pfitzinger, J., & Katzke, N. (2019). A constrained hierarchical risk parity algorithm withcluster-based capital allocation. Stellenbosch University, Department ofEconomics.Prajogo, A. U. (2011). Analyzing patterns in the equity market: ETF investor sentimentand corporate cash holding. Princeton University.Visser, I., Raijmakers, M. E., & Molenaar, P. C. (2000). Confidence intervals for hiddenMarkov model parameters. British journal of mathematical and statisticalpsychology, 53(2), 317-327.Wang, M., Lin, Y. H., & Mikhelson, I. (2020). Regime-switching factor investing withhidden Markov models. Journal of Risk and Financial Management, 13(12), 311.Yue, S., Wang, X., & Wei, M. (2008). Application of two-order difference to gapstatistic. Transactions of Tianjin University, 14(3), 217-221. 描述 碩士
國立政治大學
金融學系
109352027資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109352027 資料類型 thesis dc.contributor.advisor 江彌修 zh_TW dc.contributor.advisor Chiang, Mi-Hsiu en_US dc.contributor.author (Authors) 盧建豪 zh_TW dc.contributor.author (Authors) Lu, Chien-Hou en_US dc.creator (作者) 盧建豪 zh_TW dc.creator (作者) Lu, Chien-Hou en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-Aug-2022 17:30:05 (UTC+8) - dc.date.available 1-Aug-2022 17:30:05 (UTC+8) - dc.date.issued (上傳時間) 1-Aug-2022 17:30:05 (UTC+8) - dc.identifier (Other Identifiers) G0109352027 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/141066 - 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) 109352027 zh_TW dc.description.abstract (摘要) 本文探討隱藏式馬可夫狀態轉換模型是否能夠使投資組合績效上升。基於隱藏式馬可夫模型對台灣加權指數進行狀態分類後,得到兩種狀態:高波動低報酬狀態與低波動高報酬狀態。本文建立逆變異數加權、分層式風險評價與二次規劃最小化變異數三個投資組合,並採用 2007 年 1 月 4 日至 2021 年 12 月 31 日的台灣股市資料與美債報酬進行回測。實證發現,狀態轉換下的動態資產配置能使投資組合的夏普比率、索提諾比率與最大策略虧損報酬上升,其中又以加入狀態轉換模型的逆變異數加權投資組合表現最佳。 zh_TW dc.description.abstract (摘要) This paper explores whether a hidden Markov regime-switching model can improve portfolio performance. After we classify the Taiwan Weighted Index based on the Hidden Markov Model, two states are obtained: the state of high volatility and low return, and the state of low volatility and high return. This paper constructs three portfolios: inverse variance weighting, hierarchical risk parity and quadratic programming minimizing variance. We conduct backtests based on Taiwan stock market and U.S. bond data from January 4, 2007 to December 31, 2021. We find thatthe dynamic asset allocation under the regime-switching model can increase the Sharpe ratio, Sortino ratio and maximum drawdown return of the portfolio. The inversevariance weighted portfolio under the regime-switching model performs the best. en_US dc.description.tableofcontents 第一章 緒論 1第二章 文獻回顧 4第三章 研究方法 7第一節 隱藏式馬可夫模型 7第二節 原始投資組合 8第三節 限制股債比例投資組合 12第四節 股債分別優化投資組合 12第五節 投資組合比較 13第四章 實證結果與分析 15第一節 資料敘述 15第二節 隱藏式馬可夫模型 17第三節 無限制股債比例投組 22第四節 狀態轉換機率投資組合 25第五節 股債分別優化 28第六節 投資組合比較 31第五章 結論與後續建議 36參考文獻 38 zh_TW dc.format.extent 2843961 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109352027 en_US dc.subject (關鍵詞) 資產配置 zh_TW dc.subject (關鍵詞) 隱藏式馬可夫模型 zh_TW dc.subject (關鍵詞) 狀態轉換模型 zh_TW dc.subject (關鍵詞) 分層式風險平價 zh_TW dc.subject (關鍵詞) Asset Allocation en_US dc.subject (關鍵詞) Hidden Markov Model en_US dc.subject (關鍵詞) Regime-switching Model en_US dc.subject (關鍵詞) Hierarchical Risk Parity en_US dc.title (題名) 隱藏式馬可夫狀態轉換模型下的動態資產配置 zh_TW dc.title (題名) Dynamic Asset Allocation under Hidden Markov Regime Switching Model en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Ang, A., & Bekaert, G. (2002). International asset allocation with regime shifts. Thereview of financial studies, 15(4), 1137-1187.Bailey, D. H., & Lopez de Prado, M. (2012). The Sharpe ratio efficient frontier. Journalof Risk, 15(2), 13.Bulla, J., Mergner, S., Bulla, I., Sesboüé, A., & Chesneau, C. (2011). Markov-switchingasset allocation: Do profitable strategies exist?. Journal of AssetManagement, 12(5), 310-321.Cajas, D. (2022). Riskfolio-lib (3.0.0). Retrieved fromhttps://github.com/dcajasn/Riskfolio-LibCosta, G., & Kwon, R. (2020). A Regime-Switching Factor Model for Mean-VarianceOptimization. Journal of Risk.De Prado, M. L. (2016). Building diversified portfolios that outperform out ofsample. The Journal of Portfolio Management, 42(4), 59-69.Konstantinov, G., Chorus, A., & Rebmann, J. (2020). A network and machine learningapproach to factor, asset, and blended allocation. The Journal of PortfolioManagement, 46(6), 54-71.Kritzman, M., Page, S., & Turkington, D. (2012). Regime shifts: Implications fordynamic strategies (corrected). Financial Analysts Journal, 68(3), 22-39.Lo, A. W. (2002). The statistics of Sharpe ratios. Financial analysts journal, 58(4), 36-52.Meucci, A. (2009). Managing diversification. Risk, 74-79.Nystrup, P. (2014). Regime-based asset allocation. Do profitable strategiesexist. Master`s thesis, Technical University of Denmark.Nystrup, P., Madsen, H., & Lindström, E. (2017). Long memory of financial time series39and hidden Markov models with time‐varying parameters. Journal ofForecasting, 36(8), 989-1002.Papenbrock, J. (2011). Asset Clusters and Asset Networks in Financial RiskManagement and Portfolio Optimization (Doctoral dissertation, Dissertation,Karlsruhe, Karlsruher Institut für Technologie (KIT), 2011).Pfitzinger, J., & Katzke, N. (2019). A constrained hierarchical risk parity algorithm withcluster-based capital allocation. Stellenbosch University, Department ofEconomics.Prajogo, A. U. (2011). Analyzing patterns in the equity market: ETF investor sentimentand corporate cash holding. Princeton University.Visser, I., Raijmakers, M. E., & Molenaar, P. C. (2000). Confidence intervals for hiddenMarkov model parameters. British journal of mathematical and statisticalpsychology, 53(2), 317-327.Wang, M., Lin, Y. H., & Mikhelson, I. (2020). Regime-switching factor investing withhidden Markov models. Journal of Risk and Financial Management, 13(12), 311.Yue, S., Wang, X., & Wei, M. (2008). Application of two-order difference to gapstatistic. Transactions of Tianjin University, 14(3), 217-221. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200938 en_US