TY - GEN
T1 - Portfolio Management based on Deep Reinforcement Learning with Adaptive Sampling
AU - Miao, Yu Hsiang
AU - Hsiao, Yi Ting
AU - Huang, Szu Hao
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - Quantitative trading finds stable and profitable trading strategies by observing historical data through statistics or mathematics methods. However, existing studies are still insufficient for the generalization of trading strategies. Therefore, this study takes the constituents of the Dow Jones Industrial Average as the target and applies the problem of optimizing the portfolio. The goal is to construct a portfolio of five assets from the constituent stocks, and this portfolio could achieve excellent performance through our trading strategy. Also, this study proposes a sampling strategy to determine which data is worth learning by observing the learning condition in order to save computational time. From the result of the experiment, we could observe that the model with our sampling strategy performed 6-7 % better than our baselines in terms of Sharpe ratio.
AB - Quantitative trading finds stable and profitable trading strategies by observing historical data through statistics or mathematics methods. However, existing studies are still insufficient for the generalization of trading strategies. Therefore, this study takes the constituents of the Dow Jones Industrial Average as the target and applies the problem of optimizing the portfolio. The goal is to construct a portfolio of five assets from the constituent stocks, and this portfolio could achieve excellent performance through our trading strategy. Also, this study proposes a sampling strategy to determine which data is worth learning by observing the learning condition in order to save computational time. From the result of the experiment, we could observe that the model with our sampling strategy performed 6-7 % better than our baselines in terms of Sharpe ratio.
KW - Deep learning
KW - Portfolio management
KW - Reinforcement Learning
UR - http://www.scopus.com/inward/record.url?scp=85100035882&partnerID=8YFLogxK
U2 - 10.1109/ICPAI51961.2020.00031
DO - 10.1109/ICPAI51961.2020.00031
M3 - Conference contribution
AN - SCOPUS:85100035882
T3 - Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
SP - 130
EP - 133
BT - Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020
Y2 - 3 December 2020 through 5 December 2020
ER -