在現代投資組合理論中，最基本的模型是 mean-variance model，然而以此模型算出之最適權重易受到估計參數變動的結果；再者，亦有前後兩期同資產權重差異過大的情形發生，這些狀況在實務中會對投資者造成操作的困難。而在 1991 年被提出之 Black-Litterman model 結合 mean-variance model、 CAPM、貝氏估計法，除了解決前述權重敏感的問題，亦容許投資人加入其對於投組內資產報酬率的觀點於模型中，且觀點的建立十分具有彈性。本文利用文字探勘技術，分析公司法說會紀錄來預測資產報酬率，以此建立觀點，加入 Black-Litterman model 來做投資組合的探討。結果顯示，在觀點的建構下，加入文本情緒指標的模型與單純自我迴歸模型和其加入 3 個總經變數之觀點模型相比，加入文本情緒指標的模型所建構出的投資組合表現皆會比後兩者好，同時勝於大盤與傳統 mean-variance model；且我們也發現文字情緒可以作為資產報酬預測的依據。

In modern portfolio theory, Markowitz mean-variance approach is the most traditional and widely-used one. However, the optimal weights are sensitive to the estimation of parameters and also tend to change significantly. These will make it difficult for practitioners to optimize by this approach. The Black-Litterman model (1991) combining mean-variance optimization, CAPM and Bayesian estimation deals with these issues. Furthermore, it allows the investors to build their own views about returns, which are very flexible. In this thesis, we apply text analysis to the transcripts of conference call to predict stock returns, and then form the views. Finally, we optimize the weights by Black-Litterman approach and see the performance of optimal portfolios. Our results show that portfolios optimized by Black-Litterman models which include tone index in view constructing outperform the benchmark portfolio, mean-variance model portfolio and portfolios without tone index. In the meanwhile, we suggest that tone index can be a predictor of stock returns.

摘要 i
Abstract ii
誌謝辭 iii
目錄 iv
圖目錄 v
表目錄 vi
1. 前言 1
2. 文獻回顧 2
3. 研究方法 4
4. 實證結果分析 11
5. 結論 18
參考文獻 21

1. Beach, S.L. and A.G. Orlov (2007), “An Application of the Black-Litterman Model With EGARCH-M-derived Views for International Portfolio Management,” Financial Markets and Portfolio Management, 21, 147-166.
2. Becker, F. and M. Gürtler (2010), “Quantitative Forecast Model for the Application of the Black-Litterman Approach,” Paris December 2009 Finance International Meeting AFFI – EUROFIDAI.
3. Bevan, A. and K. Winkelmann (1998), “Using the Black-Litterman Global Asset Allocation Model: Three Years of Practical Experience,” Fixed Income Research, Goldman, Sachs & Co.
4. Black, F. and R. Litterman (1992), “Global Portfolio Optimization,” Financial Analysts Journal, 48, 28-43.
5. Brockman, P., X. Li, and S.M. Price (2015), “Differences in Conference Call Tones: Managers Versus Analysts,” Financial Analysts Journal, 71, 24-42.
6. Didenko, A. and S. Demicheva (2013), “Application of Ensemble Learning for Views Generation in Meucci Portfolio Optimization Framework,” Review of Business and Economics Studies, 1, 100-110.
7. Doran, J.S., D.R. Peterson, and S.M. Price (2012), “Earnings Conference Call Content and Stock Price: The Case of REITs,” Journal of Real Estate Finance and Economics, 45, 402-434.
8. Duqi A., L. Franci, and G. Torluccio (2014), “The Black-Litterman Model: The Definition of Views Based on Volatility Forecasts,” Applied Financial Economics, 24, 1285-1296.
9. He, G. and R. Litterman (1999), “The Intuition Behind Black-Litterman Model Portfolios,” Investment Management Research, Goldman, Sachs & Co.
10. Henry, E. (2008), “Are Investors Influenced by How Earnings Press Releases Are Written?” The Journal of Business Communication, 45, 363–407.
11. Idzorek, T. (2007), “A Step-by-step Guide to the Black-Litterman Model: Incorporating User-specified Confidence Levels,” Forecasting Expected Returns in the Financial Markets, 17-38.
12. Kara, M., A. Ulucan, and K.B. Atici (2019), “A Hybrid Approach for Generating Investor Views in Black–Litterman Model,” Expert Systems with Applications, 128, 256-270.
13. Loughran, T. and B. Mcdonald (2011), “When Is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10‐Ks,” Journal of finance, 66, 35-65.
14. Mankert, C. and M.J. Seiler (2011), “Mathematical Derivations and Practical Implications for the Use of the Black-Litterman Model,” Journal of Real Estate Portfolio Management, 17, 139-159.
15. Meucci, A. (2010), “The Black-Litterman Approach: Original Model and Extensions,” Shorter version in The Encyclopedia of Quantitative Finance.
16. Palomba, G. (2008), “Multivariate GARCH Models and the Black-Litterman Approach For Tracking Error Constrained Portfolios: An Empirical Analysis,” Global Business and Economics Review, 10, 379-413.
17. Price, S., J.S. Doran, D.R. Peterson, and B.A. Bliss (2012), “Earnings Conference Calls and Stock Returns: The Incremental Informativeness of Textual Tone,” Journal of Banking & Finance, 36, 992-1011.
18. Sadique, S., F. In, and M. Veeraraghavan (2008), “The Impact of Spin and Tone on Stock Returns and Volatility: Evidence from Firm-Issued Earnings Announcements and the Related Press Coverage,” https://ssrn.com/abstract=1121231.
19. Sadique, S., F. In, M. Veeraraghavan, and P. Wachtel (2013), “Soft Information and Economic Activity: Evidence from the Beige Book,” Journal of Macroeconomics, 37, 81-92.
20. Satchell, S. and A. Scowcroft (2000), “A Demystification of the Black–Litterman Model: Managing Quantitative and Traditional Portfolio Construction,” Journal of Asset Management, 1, 138-150.
21. Walters, J. (2014), “The Black-Litterman Model in Detail,” blacklitterman.org.