Risk-aware Regularization for Opinion-based Portfolio Selection
DOI:
https://doi.org/10.1609/icwsm.v15i1.18134Keywords:
Measuring predictability of real world phenomena based on social media, e.g., spanning politics, finance, and health, Subjectivity in textual data; sentiment analysis; polarity/opinion identification and extraction, linguistic analyses of social media behaviorAbstract
Every investor faces the risk-return tradeoff when making investment decisions. Most of the investors construct a portfolio instead of putting all of their wealth on a certain stock. However, most of the previous works in the NLP community focus on predicting the movement of stocks' prices or volatilities, but do not consider the portfolio selection issue. On the other hand, few works consider unstructured data in the financial community when dealing with this issue. This paper introduces a novel opinion-based portfolio selection task, and proposes new objective functions presenting different risk appetites of investors. The empirical studies of the selecting portfolio are also discussed with both Sharpe ratio and volatility metrics.Downloads
Published
2021-05-22
How to Cite
Hsu, T.-W., Chen, C.-C., Huang, H.-H., & Chen, H.-H. (2021). Risk-aware Regularization for Opinion-based Portfolio Selection. Proceedings of the International AAAI Conference on Web and Social Media, 15(1), 1080-1084. https://doi.org/10.1609/icwsm.v15i1.18134
Issue
Section
Poster Papers