Responsive image
博碩士論文 etd-0725122-004837 詳細資訊
Title page for etd-0725122-004837
論文名稱
Title
XGBoost因子擇時結合Black-Litterman建立美股投資組合
Construct a US Stock Portfolio by Using XGBoost Factor Timing with Black-Litterman Model
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
95
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2022-07-05
繳交日期
Date of Submission
2022-08-25
關鍵字
Keywords
因子擇時、XGBoost模型、Barra模型、Black-Litterman、投資組合
Factor Timing, XGBoost Model, Barra Model, Black-Litterman, Investment Portfolio
統計
Statistics
本論文已被瀏覽 210 次,被下載 0
The thesis/dissertation has been browsed 210 times, has been downloaded 0 times.
中文摘要
台灣Smart Beta ETF近年受到投資者歡迎,在2021年時的自然成長率高達75%,高居亞洲首位,遠高於亞洲及太平洋地區第二的澳洲的20.2%。高成長率使得規模也超越中國,成為亞洲及太平洋地區第三大市場,僅次於日本及澳洲。而台灣Smart Beta ETF占總ETF比重也達到9.3%。
本研究以S&P500歷史成分股為股票池,建立多因子擇時投資組合。首先參照Barra USE4估算要素並合成風格因子,再進一步求出因子報酬與風險預測矩陣。用擴展窗口法(the expanding window approach)訓練XGBoost模型以總體經濟指標等特徵來預測未來風格因子報酬,並將其作為Black-Litterman模型中的投資人觀點,以每個月一次的頻率做動態調整,進行2013年至2021年的績效回測並對各個參數做敏感度分析。經由實證發現(1)多因子擇時投資組合的年化報酬、年化波動率、夏普比率都比S&P500指數來得更好,不過月周轉率高達55%;(2)Barra USE4風險預測模型能有效降低投資組合的年化波動率;(3)XGBoost模型能有效預測未來風格因子報酬的相對關係。
Abstract
Smart Beta ETFs are becoming more and more popular among investors in Taiwan. The natural growth rate is 75% in 2021, which is the highest in the Asia-Pacific. Meanwhile, the rate in Taiwan is 75%; much higher than second-placer Australia's 20.2%. Taiwan also surpassed China’s growth rate, becoming the third largest market in the Asia-Pacific. This is just behind Japan and Australia. Smart Beta ETFs in Taiwan also account for 9.3% of total ETF market shares.
The forecast results are used as the investor's view in the Black-Litterman model, and the portfolio is dynamically adjusted once a month. Below is the observed sensitivity analysis of the parameters and portfolio performance from 2013 to 2021: (1) the annualized return, annualized volatility, and Sharpe ratio of the multi-factor portfolio outperform the S&P500 index, but the monthly turnover rate is as high as 55%; (2) the Barra USE4 risk prediction model can effectively reduce the annualized portfolio volatility; and (3) the XGBoost model can effectively predict the relative relationship among the future style factor returns.
目次 Table of Contents
論文審定書 i
摘要 ii
ABSTRACT iii
Content iv
List of Figures vii
List of Tables viii
1. Introduction 1
1-1. General Background Information and Research Motivation 1
1-2. Research Purpose 3
1-3. Research Framework 4
2. Literature review 6
2-1. Capital Asset Pricing Model 6
2-2. Multifactor Model 7
2-3. Factor Timing 8
2-3-1. Factor Valuation Timing 9
2-3-2. Factor Momentum Timing 9
2-3-3. Factor Volatility Timing 10
2-3-4. Market Sentiment Timing 10
2-3-5. Economic Cycle Timing 10
2-4. Machine Learning 11
2-4-1. General Linear Model 12
2-4-2. Nonlinear Model 13
2-4-3. Deep Learning 14
2-4-4. Machine Learning in Asset Pricing 14
3. Research Methodology 16
3-1. Research Process 16
3-2. Research Data 20
3-2-1. Usage Data and Period Range 20
3-2-2. Building Factor and Sorting Data 21
3-3. BARRA USE4 Model 25
3-3-1. Calculating Factor Returns 25
3-3-2. Modeling Covariance Matrices 27
3-3-3. Eigenfactor Risk Adjustment 28
3-4. XGBoost Model 31
3-5. Black-Litterman Model 35
4. Empirical Results 46
4-1. Information Gain Ratio 46
4-2. Investment Portfolio 48
4-3. Sensitivity Analysis 52
5. Conclusions and Suggestions 61
5-1. Conclusions 61
5-2. Suggestions 64
References 66
Appendix A Tables and Figures 69
Appendix B Style Factor Characteristic Importance Table 76
參考文獻 References
Arnott, R., Harvey, C. R., Kalesnik, V., & Linnainmaa, J. (2019). Alice’s adventures in factorland: Three blunders that plague factor investing. The Journal of Portfolio Management, 45(4), 18-36.
Asness, C., Chandra, S., Ilmanen, A., & Israel, R. (2017). Contrarian factor timing is deceptively difficult. The Journal of Portfolio Management, 43(5), 72-87.
Asness, C. S., Friedman, J. A., Krail, R. J., & Liew, J. M. (2000). Style timing: Value versus growth. The Journal of Portfolio Management, 26(3), 50-60.
Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross‐section of stock returns. The journal of finance, 61(4), 1645-1680.
Bender, J., Sun, X., Thomas, R., & Zdorovtsov, V. (2018). The promises and pitfalls of factor timing. The Journal of Portfolio Management, 44(4), 79-92.
Black, F., & Litterman, R. (1992). Global portfolio optimization. Financial Analysts Journal, 48(5), 28-43.
Blitz, D., Van Vliet, P., & Baltussen, G. (2019). The volatility effect revisited. The Journal of Portfolio Management, 46(2), 45-63.
Carhart, M. M. (1997). On persistence in mutual fund performance. The journal of finance, 52(1), 57-82.
Chen, J., Tang, G., Yao, J., & Zhou, G. (2022). Investor attention and stock returns. Journal of Financial and Quantitative Analysis, 57(2), 455-484.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining,
Chopra, V. K., & Ziemba, W. T. (2013). The effect of errors in means, variances, and covariances on optimal portfolio choice. In Handbook of the fundamentals of financial decision making: Part I (pp. 365-373). World Scientific.
Connor, G., & Korajczyk, R. A. (1995). The arbitrage pricing theory and multifactor models of asset returns. Handbooks in operations research and management science, 9, 87-144.
Cox, J. C., & Ross, S. A. (1976). A survey of some new results in financial option pricing theory. The journal of finance, 31(2), 383-402.
Daniel, K., Hirshleifer, D., & Sun, L. (2020). Short-and long-horizon behavioral factors. The Review of Financial Studies, 33(4), 1673-1736.
Diebold, F. X., & Mariano, R. S. (2002). Comparing predictive accuracy. Journal of Business & economic statistics, 20(1), 134-144.
Ehsani, S., & Linnainmaa, J. (2019). Factor Momentum and the Momentum Factor.
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The journal of finance, 25(2), 383-417.
Fama, E. F., & French, K. R. (1992). The cross‐section of expected stock returns. The journal of finance, 47(2), 427-465.
Fama, E. F., & French, K. R. (2015). A five-factor asset pricing model. Journal of financial economics, 116(1), 1-22.
Gordon, M. J. (1962). The savings investment and valuation of a corporation. The Review of Economics and Statistics, 37-51.
Grinold, R. C., & Kahn, R. N. (2000). Active portfolio management.
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223-2273.
Gupta, T., & Kelly, B. (2019). Factor momentum everywhere. The Journal of Portfolio Management, 45(3), 13-36.
Han, Y., He, A., Rapach, D., & Zhou, G. (2019). Firm characteristics and expected stock returns. Available at SSRN.
Hou, K., Xue, C., & Zhang, L. (2015). Digesting anomalies: An investment approach. The Review of Financial Studies, 28(3), 650-705.
Jegadeesh, N., & Titman, S. (1993). Returns to buying winners and selling losers: Implications for stock market efficiency. The journal of finance, 48(1), 65-91.
Lintner, J. (1965). Security prices, risk, and maximal gains from diversification. The journal of finance, 20(4), 587-615.
Mankert, C. (2006). The Black-Litterman Model: mathematical and behavioral finance approaches towards its use in practice KTH].
Markowitz, H. (1952). The utility of wealth. Journal of political Economy, 60(2), 151-158.
Menchero, J., Orr, D., & Wang, J. (2011). The Barra US equity model (USE4), methodology notes. English, MSCI (May.
Menchero, J., Wang, J., & Orr, D. J. (2012). Improving risk forecasts for optimized portfolios. Financial Analysts Journal, 68(3), 40-50.
Miller, K. L., Li, H., Zhou, T. G., & Giamouridis, D. (2015). A risk-oriented model for factor timing decisions. The Journal of Portfolio Management, 41(3), 46-58.
Mossin, J. (1966). Equilibrium in a capital asset market. Econometrica: Journal of the econometric society, 768-783.
Muller, P. (1993). Empirical tests of biases in equity portfolio optimization. Cambridge University Press Cambridge, UK.
Qian, E. (2005). Risk parity portfolios: Efficient portfolios through true diversification. Panagora Asset Management.
Rabener, N. (2018). FACTOR ALLOCATION MODELS: Improving Factor Portfolio Efficiency. https://finkaizen.com/research-factor-allocation-models
Rapach, D. E., Strauss, J. K., & Zhou, G. (2010). Out-of-sample equity premium prediction: Combination forecasts and links to the real economy. The Review of Financial Studies, 23(2), 821-862.
Reilly, F. K., & Brown, K. C. (2011). Investment analysis and portfolio management. Cengage Learning.
Sharpe, W. F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. The journal of finance, 19(3), 425-442.
Sharpe, W. F. (1974). Imputing expected security returns from portfolio composition. Journal of Financial and Quantitative Analysis, 9(3), 463-472.
Shepard, P. G. (2009). Second order risk. arXiv preprint arXiv:0908.2455.
Treynor, J. L. (1961). Market value, time, and risk. Time, and Risk (August 8, 1961).
Treynor, J. L. (1962). Jack treynor's' toward a theory of market value of risky assets'. Available at SSRN 628187.
Ung, D., & Luk, P. (2016). What Is in Your Smart Beta Portfolio? A Fundamental and Macroeconomic Analysis. The Journal of Index Investing, 7(1), 49-77.

電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus:開放下載的時間 available 2025-08-25
校外 Off-campus:開放下載的時間 available 2025-08-25

您的 IP(校外) 位址是 50.17.63.57
現在時間是 2024-03-29
論文校外開放下載的時間是 2025-08-25

Your IP address is 50.17.63.57
The current date is 2024-03-29
This thesis will be available to you on 2025-08-25.

紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code