摘要(英) |
Designing a profitable trading strategy based on different situations is a major challenge in
stock trading. In recent years, the development of artificial intelligence has brought new investment methods to the stock market. Q-learning, a reinforcement learning algorithm, can
help investors to learn market trends and recommend more reasonable investment decisions.
In Q-learning, the formulation of states is particularly important since different formulation methods can affect its performance. We propose a data-driven approach based on a
non-supervised learning method to set the states required in Q-learning. By utilizing multidimensional stock market data as features and leveraging Dynamic Time Warping (DTW) and t-SNE, the proposed approach efficiently identifies the desired states for Q-learning. In this work, using the Taiwan stock market as an example, we obtain the Q-learning investment decision of a single asset and propose an appropriate investment portfolio consisting of multiple assets accordingly. The empirical results reveal that the proposed method provides a satisfactory investment performance. |
參考文獻 |
C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, King’s College, Cambridge, England, 1989.
C. J. C. H. Watkins and P. Dayan. Q-learning. Machine Learning, 3:279–292, 1992.
D. Berndt & J. Clifford. Using dynamic time warping to find patterns in time series. AAAI94 Workshop on Knowledge Discovery in Databases (KDD-94), Seattle, Washington,
1994.
H. Sakoe and S. Chiba. Dynamic Programming Algorithm Optimization for Spoken Word
Recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26, 43-49,
1978.
J. B. Chakole et al. A Q-learning agent for automated trading in equity stock markets.
Expert Systems with Applications, Vol. 163, 113761, ISSN 0957-4174, 2021.
J. Hu and M. P. Wellman. Nash Q-Learning for General-Sum Stochastic Games. Journal
of Machine Learning Research, 2003.
K. Y. Wong and F. L. Chung. Visualizing Time Series Data with Temporal Matching Based
t-SNE. International Joint Conference on Neural Networks, Budapest, Hungary, pages
14-19, 2019.
L. Bu¸soniu, R. Babu˘ska, and B. De Schutter. Multi-agent reinforcement learning: An
overview. Chapter 7 in Innovations in Multi-Agent Systems and Applications – 1 (D.
Srinivasan and L.C. Jain, eds.), vol. 310 of Studies in Computational Intelligence,
Berlin, Germany: Springer, pp. 183–221, 2010.
L. v. d. Maaten and G. Hinton. Visualizing Data using t-SNE. Journal of Machine Learning
Research, 2008.
M. L. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming.
John Wiley & Sons, New York, 1994.
R. S. Sutton & A. G. Barto. Reinforcement Learning: An Introduction. MIT Press, 2018. |