請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80326完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 曹承礎(Seng-Cho Chou) | |
| dc.contributor.author | MIN-XUE HUA | en |
| dc.contributor.author | 華敏學 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:04:31Z | - |
| dc.date.available | 2021-07-08 | |
| dc.date.available | 2022-11-24T03:04:31Z | - |
| dc.date.copyright | 2021-07-08 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-06-24 | |
| dc.identifier.citation | [1]Harry Markowitz. Portfolio Selection [J]. The Journal of Finance, 1952. 7: 77- 91. [2]William F. Sharpe. Capital Asset Prices: a theory of market equilibrium under conditions of risk [J]. The Journal of Finance, 1964. 9. 1X(3):425-442. [3]John Lintner. The valuation of risk assets and the selection of risky investments and capital budgets[J]. The view of economics and statistics, 1965. 2. V 01. 47, No. 1:13-37. [4]Mossin Jan. Equilibrium in a capital asset market[J]. Journal of the Econometric Society, 1966:768-783. [5]Merton. R. An intertemporal Asset Pricing Model[J]. Econometrica 1973, 11: 867-887. [6]Scherer. B. Can Robust Portfolio Optimizaton Help to Build Better Portfolios[J]. Journal of Asset Management 2007, Vbl. 7, 374-387. [7]Chow. T, J. Hsu, V. Kalesnik and B. Little. A survey of Alternative Index Strat egies [J]. Financial Analysis Journal, 2011, Vol. 67:37-57. [8]Maillard. S, Roncalli. T and Teiletche. J. The Properties of equally-weighted ris k Contributions portfolios[J]. The Journal of Portfolio Management, 2010. 36. 4:60-70. [9]Bai. X, Scheinberg. K, and Tutuncu. R. Least-Squares approach to risk parity in portfolio selection [J]. Quantitative Fiance, 2013. 16(3):1-20. [10]Thierry Roncalli, Guillaume Weisang. Risk Parity with Risk Factors [M]. MP RA, 2012. 1. [11]Williams. P. Factor Based Approaches to Risk Parity [J]. Financial Analysis Journal, 2013. 3 [12]Fama E F. The Behavior of Stock Market Prices [J]. Journal of Business and Psychology, 1965, 38(1): 34-105. [13]Morgan I G. Stock Prices and Heteroscedasticity[J]. Journal of Business and Psychology, 1976, 49(4): 496-508. [14]Engle R F, Bollerslev T. Modelling the Persistence of Conditional Variances [J]. Econometric reviews, 1986, 5(1): 1-50. [15]Robinson G. The Effect of Futures Trading on Cash Market Volatility: Evidence From the London Stock Exchange [J]. Bank of England, 1993, 6(1): 35-46. [16]Jordan M I. Serial Order: A Parallel Distributed Processing Approach[M]. North-Holland: Advances In Psychology, 1997: 471-495. [17]Elman J L. Finding Structure in Time [J]. Cognitive Science, 1990, 14(2): 179-211. [18]Fornari F, Mele A. Sign and Volatility Switching ARCH Models: Theory and Applications to International Stock Markets [J]. Journal of Applied E-conometrics, 1997, 12(1): 49-65. [19]Hochreiter S, Schmidhuber J. Long Short-term Memory [J]. Neural Computation, 1997, 9(8): 1735-1780. [20]McKenzie M, Michell H, Brooks R D, et al. A Multi-Country of Power ARCH Models and National Stock Market Returns [J]. Papers, 1998, 19(3): 377-397. [21]Graves A, Schmidhuber J. Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures [J]. Neural Networks, 2005, 18(5-6): 602-610. [22]Ozbayoglu A M, Bahadir I. Comparison of Bayesian Estimation and Neural Network Model in Stock Market Trading[M]. Berlin: Intelligent Engineering Systems through Artificial Neural Networks, 2008: 234-256. [23]Alexander C, Lazar E, Stanescu S. Forecasting VaR Using Analytic Higher Moments for GARCH Processes[J]. International Review of Financial Analysis, 2013, 30(1): 36-45. [24]Chung J, Gulcehr C, Cho K, et al. Gated Feedback Recurrent Neural N- etworks[C]//International Conference on Machine Learning, 2015: 2067-20 75. [25]Malkiel, B. G. Fama, E. F. Efficient Capital Markets: A Review of Theory and Empirical Work[J]. Journal of Finance, 1970,25(2), 383-417. [26]Ross Stephen. The arbitrage theory of capital asset pricing[J]. Journal of ec onomic theory, 1976:341-360. [27]Fama and French. Common risk factors in the returns on stocks and bonds[J]. Journal of Financial Economics 1993, 17:3-56. [28]Carhart M. M. On Persistence in Mutual Fund Performance[J]. The Journal of Finance, 1997, 52(1):57-82. [29]Haugen, R.A., Baker, N.L..Commonality in the determinants of expected stock returns[J]. Journal of Financial Economies,1996,41:401-439. [30]Carhart, 1997. On Persistence in Mutual Fund Performance. Journal of Finance, Vol.1: 57-82 [31]Titman S. K.,C. J. Wei and F. Xie,2004,'Capital Investments and Stock Returns', Journal of Financial and Quantitative Analysis ,39,677-700. [32]Fama E. F. and K. R. French. A Five-Factor Asset Pricing Model[J]. Journal of Financial Economics, 2015, 116(1):1-22. [33]Mohanram P S.Separating Winners from Losers among Low Book-to-Market Stocks using Financial Statement Analysis [J]. Social Science Electronic Publishing, 2004,10(2-3):133-170. [34]Tortoriello R. Quantitative strategies for achieving alpha [M]. McGraw Hill, 2009. [35]Plyakha. Y, Uppal. R and Vilkv. G, Why Do Equal-Weighted Portfolios Outperf orm Value-Weighted Portfolios [J]. Journal of asset management, 2015. 3. [36]Grinold, R., 2006, “A Dynamic Model of Portfolio Management,” Journal of Investment Management, 4, 5–22. [37]Garleanu, N., L. H. Pedersen, and A. Poteshman, 2008, “Demand-Based Option Pricing,” Review of Financial Studies (forthcoming). [38]Vapnik V. The Nature of Statistical Learning Theory[M]. Springer. 1995, 8(6): 988-999. [39]Fan A,Palaniswami M. Stock Selection Using Support Vector Machines[C]. Proceedings of International Joint Conference on Neural Networks. 2001, 3(3): 793-1798. [40]Cao Q, Leggio K B, Schniederjans M J. A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market[J]. Computers Operations Research,2005,32(10):2499-2512. [41]Moghaddam AH, Moghaddam M H, Esfandyari M. Stock market index prediction using artificial neural network[J]. Journal of Economics Finance Administrative Science,2016,21(41):89-93. [42]Xiong R,Nichols E P,Shen Y.Deep Learning Stock Volatility with Google Domestic Trends[J]. Papers, 2016. [43]Fischer T,Krauss C.Deep learning with long short-term memory networks for financial market predictions[J]. Fau Discussion Papers in Economics, 2017. [44]Yutong S, Zhao H. Stock selection model based on advanced AdaBoost algorithm[C]//International Conference on Modelling. IEEE, 2015. [45]KE G,MENG Q, FINLEY T, et al. Lightgbm: A highly efficient gradient boosting decision tree[C]/Advances in Neural Information Processing Systems.2017:3146-3154. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80326 | - |
| dc.description.abstract | 資產配置一直為金融市場投資者所關注，經歷多輪的牛市和熊市，如何應對各類資產價格隨著經濟景氣的變化也引起越來越多的重視。在追求收益的同時識別風險，避免資產價格劇烈波動造成的投資策略失誤，是眾多學者研究的重點。 本篇論文研究美國金融市場，依據美林時鐘理論選取包含股票類、債權類、大宗商品類、現金類的8個投資標的在2010年3月到2021年2月的日度價格數據。在收益面向和風險面向分別選取了多因子模型和風險平價模型，並結合金融計量模型和機器學習演算法，構建投資組合。 實證的結果顯示組成的多空風險平價組合和純多風險平價組合，比較其他模型有較小的最大虧損率，模型的回撤控制能力優秀。同時組合也擁有較高的夏普比率，意味著單位風險上所產生的超額收益超過其他模型的組合。結合投資的風險偏好增加槓桿，可以達到增加收益的效果。同時對波動和最大虧損有個良好的預判，避免了因資產價格震蕩引發投資心理的變化，從而減少投資決策的失誤。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:04:31Z (GMT). No. of bitstreams: 1 U0001-2306202116281100.pdf: 8927550 bytes, checksum: 3fd74fe312a11cd4a9c3c11648189f3b (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 目 錄 口試委員審定書 Ⅰ 誌謝 Ⅱ 中文摘要 Ⅲ 英文摘要 Ⅳ 第一章、緒論 1 1.1 研究背景與動機 1 1.2 研究目的 3 1.3 論文前三章的組織架構 4 第二章、文獻綜述 6 2.1 風險平價模型 6 2.2 GARCH 模型和機器學習模型 7 2.3 基於機器學習的多因子量化模型 9 第三章、數據、理論基礎與研究方法 12 3.1 數據 12 3.2 多因子量化模型 12 3.2.1 多因子模型 12 3.2.2 因子的選取和因子有效性分析 12 3.2.3 基於 LightGBM 模型的多因子模型 14 3.3 風險平價模型和模型參數計算的改進 15 3.3.1 風險平價模型的定義 15 3.3.2 風險平價模型參數計算的改進 （GARCH 模型） 16 3.3.3 風險平價模型參數計算的改進 (GARCH 模型結合 LSTM 模型） 17 3.4 評估標準 19 第四章、實證分析 21 4.1 基於LightGBM 的多因子模型 22 4.2 利用 GARCH + LSTM 改進風險平價模型的參數計算 26 4.3 構建投資組合 31 第五章、結論與建議 35 5.1 研究結論 35 5.2 研究限制與建議 36 參考文獻 37 附錄 41 圖目錄 圖1：美林時鐘 2 圖2：RNN 網路結構 18 圖3：LSTM 結構 18 圖4：主要架構和流程圖 21 圖5：各資產的時間序列圖 22 圖6：各個因子的相關係數矩陣 24 圖7：納斯達克指數的序列圖、自相關圖、偏自相關圖和QQ圖、概率圖 27 圖8：GARCH+LSTM 混合模型架構的圖示 30 圖9：各組合回測期間的走勢 32 圖10：各組合回測期間的最大虧損序列 33 圖11：加槓桿的多空風險平價組合 34 表目錄 表1：IC值和IR比率的因子評價體系 13 表2：各資產的日度收益率（部分展示） 22 表3：各資產的技術類因子值（部分展示） 23 表4：IC 值和 IR 值 24 表5：各個因子的方差膨脹係數 25 表6：LightGBM 模型主要的 Hyperparamter 25 表7：各資產的ADF檢驗結果 26 表8：各資產的定階結果 28 表9：白銀指數的 GARCH 模型構建（1） 28 表10：白銀指數的 GARCH 模型構建（2） 29 表11：白銀指數的 GARCH 模型構建（3） 29 表12：LSTM 輸入項 30 表13：MAE 對比 31 表14：各組合回測期間的表現 33 表15：加槓桿的多空風險平價組合的表現對比 34 | |
| dc.language.iso | zh-TW | |
| dc.subject | 機器學習模型 | zh_TW |
| dc.subject | 資產價格波動 | zh_TW |
| dc.subject | 多因子模型 | zh_TW |
| dc.subject | 風險平價模型 | zh_TW |
| dc.subject | machine learning model | en |
| dc.subject | risk parity model | en |
| dc.subject | multi-factor model | en |
| dc.subject | asset price volatility | en |
| dc.title | 結合多因子與風險平價模型於資產管理的應用 | zh_TW |
| dc.title | The application of multi-factor model and risk parity model to asset management | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳建錦(Hsin-Tsai Liu),陳鴻基(Chih-Yang Tseng) | |
| dc.subject.keyword | 資產價格波動,多因子模型,風險平價模型,機器學習模型, | zh_TW |
| dc.subject.keyword | asset price volatility,multi-factor model,risk parity model,machine learning model, | en |
| dc.relation.page | 42 | |
| dc.identifier.doi | 10.6342/NTU202101105 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-06-24 | |
| dc.contributor.author-college | 管理學院 | zh_TW |
| dc.contributor.author-dept | 資訊管理學研究所 | zh_TW |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2306202116281100.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 8.72 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。