許多公司都利用Black-Litterman模型提供投資組合自動化的服務，包括高盛、Betterment、Vanguard等知名投資組合自動化服務企業。Black-Litterman模型讓投資者能夠結合投資者主觀的觀點以及市場均衡報酬建構出符合投資者期待的投資組合。在投資者主觀的觀點中，有兩種不同的觀點，分別是絕對觀點以及相對觀點。近來，由於建構投資者觀點上有許多困難，因此許多研究使用機器學習方法建構投資者觀點。比如：透過value-based或text-based的股價預測模型預測每個投資標的未來的報酬，進而建構投資者之絕對觀點。但是，這些研究有兩個共同的缺點：準確預測每個投資標的之絕對表現是很困難的以及忽視了文字背後彼此的重要關聯性。
在此篇論文中，我們透過基於知識圖譜的事件嵌入方法建構相對的投資觀點去解決過往研究的缺點，在實驗結果指出我們的方法比起其他投資組合模型能夠建構出在同樣的單位風險下創造出更高收益的投資組合。

Many companies, including Goldman Sachs, Betterment, Vanguard, used the Black-Litterman model for investment management. The Black-Litterman model allows an investor to incorporate his view on certain assets with the market equilibrium returns of the assets to formulate the posterior expected return. There are two kinds of investor’s views: the absolute view and the relative view. However, it isn't easy to construct an investor’s view. Recently, many researchers used machine learning methods to build investor’s views. For example, recent research used value-based or text-based models to predict every asset's return in a portfolio to construct an absolute investor’s view. However, these models have two common drawbacks, including (1) it is difficult to predict the performance of each asset, and (2) they ignored the crucial relations in between different terms in a text.
In this thesis, we propose to leverage the knowledge graph-based event embedding method for constructing relative view to address these two problems for portfolio constructions. The experimental results showed that the portfolios constructed using our method outperformed the other models in terms of higher return rates and lower risks.

[1] J. E. Fisch, M. Labouré, and J. A. Turner, "The Emergence of the Robo-advisor," The Disruptive Impact of FinTech on Retirement Systems, vol. 13, 2019.
[2] H. Markowitz, "The utility of wealth," Journal of political Economy, vol. 60, no. 2, pp. 151-158, 1952.
[3] F. Black and R. Litterman, "Global Portfolio Optimization," Financial Analysts Journal, vol. 48, no. 5, pp. 28-43, 1992/09/01 1992, doi: 10.2469/faj.v48.n5.28.
[4] M.-Y. Day, T.-K. Cheng, and J.-G. Li, "AI robo-advisor with big data analytics for financial services," presented at the Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Barcelona, Spain, 2018.
[5] D. Pirner and M. Fischer, "Asset Allocation with Black-Litterman in a case study of Robo Advisor Betterment," 08/01 2018.
[6] H. Wang and S. Yu, "Robo-Advising: Enhancing Investment with Inverse Optimization and Deep Reinforcement Learning," arXiv preprint arXiv:2105.09264, 2021.
[7] M. Kara, A. Ulucan, and K. B. Atici, "A hybrid approach for generating investor views in Black–Litterman model," Expert Systems with Applications, vol. 128, pp. 256-270, 2019.
[8] F. Z. Xing, E. Cambria, L. Malandri, and C. Vercellis, "Discovering Bayesian market views for intelligent asset allocation," in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2018: Springer, pp. 120-135.
[9] D. Cheng, F. Yang, X. Wang, Y. Zhang, and L. Zhang, "Knowledge Graph-based Event Embedding Framework for Financial Quantitative Investments," presented at the Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, China, 2020.
[10] P. Hájek, "Combining bag-of-words and sentiment features of annual reports to predict abnormal stock returns," Neural Computing and Applications, vol. 29, 04/01 2018, doi: 10.1007/s00521-017-3194-2.
[11] Y. Peng and H. Jiang, "Leverage financial news to predict stock price movements using word embeddings and deep neural networks," arXiv preprint arXiv:1506.07220, 2015.
[12] S. Deng, N. Zhang, W. Zhang, J. Chen, J. Z. Pan, and H. Chen, "Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network," presented at the Companion Proceedings of The 2019 World Wide Web Conference, San Francisco, USA, 2019.
[13] S. Ji, S. Pan, E. Cambria, P. Marttinen, and S. Y. Philip, "A survey on knowledge graphs: Representation, acquisition, and applications," IEEE Transactions on Neural Networks and Learning Systems, 2021.
[14] G. Angeli, M. J. J. Premkumar, and C. D. Manning, "Leveraging linguistic structure for open domain information extraction," in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2015, pp. 344-354.
[15] W. Shen, J. Wang, and J. Han, "Entity linking with a knowledge base: Issues, techniques, and solutions," IEEE Transactions on Knowledge and Data Engineering, vol. 27, no. 2, pp. 443-460, 2014.
[16] A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko, "Translating embeddings for modeling multi-relational data," Advances in neural information processing systems, vol. 26, 2013.
[17] M. J. Best and R. R. Grauer, "On the sensitivity of mean-variance-efficient portfolios to changes in asset means: some analytical and computational results," The review of financial studies, vol. 4, no. 2, pp. 315-342, 1991.
[18] R. O. Michaud, "The Markowitz optimization enigma: Is ‘optimized’optimal?," Financial analysts journal, vol. 45, no. 1, pp. 31-42, 1989.
[19] D. Avramov and G. Zhou, "Bayesian portfolio analysis," Annu. Rev. Financ. Econ., vol. 2, no. 1, pp. 25-47, 2010.
[20] W. Lee, "Advanced Theory and Methodology of Tactical Asset Allocation (Chicago: Frank J. Fabozzi Associates)," 2000.
[21] T.-J. Hsieh, H.-F. Hsiao, and W.-C. Yeh, "Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm," Applied soft computing, vol. 11, no. 2, pp. 2510-2525, 2011.
[22] K.-i. Kamijo and T. Tanigawa, "Stock price pattern recognition-a recurrent neural network approach," in 1990 IJCNN international joint conference on neural networks, 1990: IEEE, pp. 215-221.
[23] A. M. Rather, A. Agarwal, and V. Sastry, "Recurrent neural network and a hybrid model for prediction of stock returns," Expert Systems with Applications, vol. 42, no. 6, pp. 3234-3241, 2015.
[24] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[25] T. Lin, T. Guo, and K. Aberer, "Hybrid neural networks for learning the trend in time series," in Proceedings of the twenty-sixth international joint conference on artificial intelligence, 2017, no. CONF, pp. 2273-2279.
[26] Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell, "A dual-stage attention-based recurrent neural network for time series prediction," arXiv preprint arXiv:1704.02971, 2017.
[27] S. Elhammadi et al., "A High Precision Pipeline for Financial Knowledge Graph Construction," in Proceedings of the 28th International Conference on Computational Linguistics, 2020, pp. 967-977.
[28] K. Clark and C. D. Manning, "Deep reinforcement learning for mention-ranking coreference models," arXiv preprint arXiv:1609.08667, 2016.
[29] T. Trouillon, C. R. Dance, J. Welbl, S. Riedel, É. Gaussier, and G. Bouchard, "Knowledge graph completion via complex tensor factorization," arXiv preprint arXiv:1702.06879, 2017.
[30] M. Nickel, L. Rosasco, and T. Poggio, "Holographic embeddings of knowledge graphs," in Proceedings of the AAAI Conference on Artificial Intelligence, 2016, vol. 30, no. 1.
[31] T. Dettmers, P. Minervini, P. Stenetorp, and S. Riedel, "Convolutional 2d knowledge graph embeddings," in Thirty-second AAAI conference on artificial intelligence, 2018.
[32] Y. Cao, X. Wang, X. He, Z. Hu, and T.-S. Chua, "Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences," in The world wide web conference, 2019, pp. 151-161.
[33] W. F. Sharpe, "Imputing expected security returns from portfolio composition," Journal of Financial and Quantitative Analysis, vol. 9, no. 3, pp. 463-472, 1974.
[34] T. Idzorek, "A step-by-step guide to the Black-Litterman model: Incorporating user-specified confidence levels," in Forecasting expected returns in the financial markets: Elsevier, 2007, pp. 17-38.
[35] V. DeMiguel, L. Garlappi, and R. Uppal, "Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy?," The review of Financial studies, vol. 22, no. 5, pp. 1915-1953, 2009.
[36] W. F. Sharpe, "The sharpe ratio," Journal of portfolio management, vol. 21, no. 1, pp. 49-58, 1994.