Deog-Yeong Park’s research while affiliated with Kwangwoon University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (2)


Figure 6. An example of the expert's actions.
Figure 7. Architecture of the hybrid deep reinforcement learning.
Figure 12. Experimental results on the larger dataset. (a) Rate of return. (b) Sharpe ratio. (c) Maximum drawdown. Figure 12. Experimental results on the larger dataset. (a) Rate of return. (b) Sharpe ratio. (c) Maximum drawdown.
Figure 13. Experimental results of the ablation studies. (a) Rate of return. (b) Sharpe ratio. (c) Maximum drawdown.
Figure 14. Comparison of static and dynamic delays. (a) Rate of return. (b) Sharpe ratio. (c) Maximum drawdown.

+3

Hybrid Deep Reinforcement Learning for Pairs Trading
  • Article
  • Full-text available

January 2022

·

924 Reads

·

35 Citations

Applied Sciences

Sang-Ho Kim

·

Deog-Yeong Park

·

Ki-Hoon Lee

Pairs trading is an investment strategy that exploits the short-term price difference (spread) between two co-moving stocks. Recently, pairs trading methods based on deep reinforcement learning have yielded promising results. These methods can be classified into two approaches: (1) indirectly determining trading actions based on trading and stop-loss boundaries and (2) directly determining trading actions based on the spread. In the former approach, the trading boundary is completely dependent on the stop-loss boundary, which is certainly not optimal. In the latter approach, there is a risk of significant loss because of the absence of a stop-loss boundary. To overcome the disadvantages of the two approaches, we propose a hybrid deep reinforcement learning method for pairs trading called HDRL-Trader, which employs two independent reinforcement learning networks; one for determining trading actions and the other for determining stop-loss boundaries. Furthermore, HDRL-Trader incorporates novel techniques, such as dimensionality reduction, clustering, regression, behavior cloning, prioritized experience replay, and dynamic delay, into its architecture. The performance of HDRL-Trader is compared with the state-of-the-art reinforcement learning methods for pairs trading (P-DDQN, PTDQN, and P-Trader). The experimental results for twenty stock pairs in the Standard & Poor’s 500 index show that HDRL-Trader achieves an average return rate of 82.4%, which is 25.7%P higher than that of the second-best method, and yields significantly positive return rates for all stock pairs.

Download

FIGURE 5: Neural network structures
FIGURE 7: Stocks with different price trends
Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning

November 2021

·

714 Reads

·

28 Citations

IEEE Access

Algorithmic trading allows investors to avoid emotional and irrational trading decisions and helps them make profits using modern computer technology. In recent years, reinforcement learning has yielded promising results for algorithmic trading. Two prominent challenges in algorithmic trading with reinforcement learning are (1) extracting robust features and (2) learning a profitable trading policy. Another challenge is that it was previously often assumed that both long and short positions are always possible in stock trading; however, taking a short position is risky or sometimes impossible in practice. We propose a practical algorithmic trading method, SIRL-Trader, which achieves good profit using only long positions. SIRL-Trader uses offline/online state representation learning (SRL) and imitative reinforcement learning. In offline SRL, we apply dimensionality reduction and clustering to extract robust features whereas, in online SRL, we co-train a regression model with a reinforcement learning model to provide accurate state information for decision-making. In imitative reinforcement learning, we incorporate a behavior cloning technique with the twin-delayed deep deterministic policy gradient (TD3) algorithm and apply multistep learning and dynamic delay to TD3. The experimental results show that SIRL-Trader yields higher profits and offers superior generalization ability compared with state-of-the-art methods.

Citations (2)


... The selected supervised learning algorithm are K Nearest Neighbor (KNN) [24], Logistic Regression (LR) [24], Support Vector Machine (SVM) [25] and Long Short Term Memory (LSTM) [20]. The selected supervised learning algorithms include Deep Q Network (DQN) [26], Double DQN [27], Gated DQN [28] and Twin Delayed Deep Deterministic policy gradient (TD3) [29]. The traditional time series algorithms include Simple Moving Average (SMA) [30], Dual Moving Average Crossover (DMAC) [30], and Moving Average Convergence/Divergence (MACD) [30]. ...

Reference:

Attention-Based Behavioral Cloning for algorithmic trading
Hybrid Deep Reinforcement Learning for Pairs Trading

Applied Sciences

... In recent years, reinforcement learning has been widely employed for the reliable and precise prediction of stock prices and the design of portfolios (Brim, 2020;Fengqian & Chao, 2020;Kim et al., 2022;Kim & Kim, 2019;Lei et al., 2020;Li et al., 2019;Lu et al., 2021;Park & Lee, 2021;Sen, 2022d). ...

Practical Algorithmic Trading Using State Representation Learning and Imitative Reinforcement Learning

IEEE Access