Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Using Data Augmentation Based Reinforcement Learning for Daily Stock Trading

Using Data Augmentation Based Reinforcement Learning for Daily Stock Trading <jats:p>In algorithmic trading, adequate training data set is key to making profits. However, stock trading data in units of a day can not meet the great demand for reinforcement learning. To address this problem, we proposed a framework named data augmentation based reinforcement learning (DARL) which uses minute-candle data (open, high, low, close) to train the agent. The agent is then used to guide daily stock trading. In this way, we can increase the instances of data available for training in hundreds of folds, which can substantially improve the reinforcement learning effect. But not all stocks are suitable for this kind of trading. Therefore, we propose an access mechanism based on skewness and kurtosis to select stocks that can be traded properly using this algorithm. In our experiment, we find proximal policy optimization (PPO) is the most stable algorithm to achieve high risk-adjusted returns. Deep Q-learning (DQN) and soft actor critic (SAC) can beat the market in Sharp Ratio.</jats:p> http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Electronics CrossRef

Using Data Augmentation Based Reinforcement Learning for Daily Stock Trading

Electronics , Volume 9 (9): 1384 – Aug 27, 2020

Using Data Augmentation Based Reinforcement Learning for Daily Stock Trading


Abstract

<jats:p>In algorithmic trading, adequate training data set is key to making profits. However, stock trading data in units of a day can not meet the great demand for reinforcement learning. To address this problem, we proposed a framework named data augmentation based reinforcement learning (DARL) which uses minute-candle data (open, high, low, close) to train the agent. The agent is then used to guide daily stock trading. In this way, we can increase the instances of data available for training in hundreds of folds, which can substantially improve the reinforcement learning effect. But not all stocks are suitable for this kind of trading. Therefore, we propose an access mechanism based on skewness and kurtosis to select stocks that can be traded properly using this algorithm. In our experiment, we find proximal policy optimization (PPO) is the most stable algorithm to achieve high risk-adjusted returns. Deep Q-learning (DQN) and soft actor critic (SAC) can beat the market in Sharp Ratio.</jats:p>

Loading next page...
 
/lp/crossref/using-data-augmentation-based-reinforcement-learning-for-daily-stock-Lxt6kztNJV

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
CrossRef
ISSN
2079-9292
DOI
10.3390/electronics9091384
Publisher site
See Article on Publisher Site

Abstract

<jats:p>In algorithmic trading, adequate training data set is key to making profits. However, stock trading data in units of a day can not meet the great demand for reinforcement learning. To address this problem, we proposed a framework named data augmentation based reinforcement learning (DARL) which uses minute-candle data (open, high, low, close) to train the agent. The agent is then used to guide daily stock trading. In this way, we can increase the instances of data available for training in hundreds of folds, which can substantially improve the reinforcement learning effect. But not all stocks are suitable for this kind of trading. Therefore, we propose an access mechanism based on skewness and kurtosis to select stocks that can be traded properly using this algorithm. In our experiment, we find proximal policy optimization (PPO) is the most stable algorithm to achieve high risk-adjusted returns. Deep Q-learning (DQN) and soft actor critic (SAC) can beat the market in Sharp Ratio.</jats:p>

Journal

ElectronicsCrossRef

Published: Aug 27, 2020

There are no references for this article.