Stock Trading Strategies Based on Deep Reinforcement Learning

Li, Yawei; Liu, Peipei; Wang, Ze

doi:10.1155/2022/4698656

Cited by 14 publications

(8 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the AR of Ref [51] is 55.71% on APPL, and our AR is also 7% higher than them. These results further explain MS-DDQN algorithm is more effective.…”

Section: ) Performance Analysismentioning

confidence: 40%

See 1 more Smart Citation

A Novel Convolutional Neural Networks for Stock Trading Based on DDQN Algorithm

Cui

Huang²,

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In deep learning based stock trading strategy models, most of the research just use simple convolutional neural networks (CNN) to process stock data. But task-specific neural network structures have been proposed extensively, and their effectiveness has been demonstrated in computer vision (CV) and natural language processing (NLP) tasks. In this paper, we proposed a multi-scale convolutional neural feature extraction network (MS-CNN) for stock data, which can better extract stock trend features and thus make better decisions. The network structure inspired by the human stock trading model: in human behavior, we do not only look at a single set of stock data, but rather combine all the stock data, such as opening, closing, and trading volume, to make a comprehensive judgment. And humans will consider the current stock trend on different time scales, such as 3-Day Line and 5-Day Line. This is consistent with the two-dimensional convolution kernels commonly used in CV tasks, so we used convolution kernels of 3×3 and 5×5 in the network with two-dimensional convolution size and constructed a novel network structure for stock data. With double deep Q networks (DDQN) algorithm, we get the best performance for our network. The experimental results show that we can obtain high yield on the datasets of Dow Jones (DJI), AAPLE (AAPL), and General Electric (GE).

show abstract

“…In addition, the AR of Ref [51] is 55.71% on APPL, and our AR is also 7% higher than them. These results further explain MS-DDQN algorithm is more effective.…”

Section: ) Performance Analysismentioning

confidence: 40%

“…We downloaded the source code from github and took the result with its highest AR a t the same time period. • Stock trading strategies based on deep reinforcement learning: Proposed by Li et al [51]. We directly took out the experimental results (AR) as baseline.…”

Section: Baseline Methodsmentioning

confidence: 99%

A Novel Convolutional Neural Networks for Stock Trading Based on DDQN Algorithm

Cui

Huang²,

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This study was conducted in response to the challenges and findings reported in the literature regarding the use of regression models to predict returns in financial stock markets. The authors of the reference article [1] suggested that regression models should not be used for this purpose, whereas the authors of [2] reported obtaining higher profits despite market inconsistencies. The present study aims to challenge these findings and develop a trading strategy based on a customized deep neural network (DNN) to predict returns in real time.…”

Section: A Problem Findingsmentioning

confidence: 99%

Trade Ease With Machine Learning and AWS

Kamurthi

Liu

2023

IEEE Access

View full text Add to dashboard Cite

Global trading is undergoing significant changes, necessitating modifications to the trading strategies. This study presents a newly developed cloud-based trading strategy that uses Amazon Web Services (AWS), machine learning (ML), and data science to automate trading tasks. The study begins by creating a machine learning trading strategy using a customized deep neural network (DNN). The strategy was then tested using a trading station before deployment on a cloud machine. The execution of the strategy resulted in a total profit of 42.74526 USD, with a test accuracy score of 87.45% and a training accuracy score of 89.15% over 6047 epochs. The roadmap provides a step-by-step overview of the entire process from strategy development to execution. In addition, this study offers insights into related issues and solutions that can enhance the effectiveness of trading strategies. Overall, this study contributes significantly to the field of cloud-based trading strategies and opens avenues for future research.

show abstract

“…Researchers have integrated RL with deep neural networks, enabling the development of DRL methods for learning trading strategies from historical data. These approaches can be classified into three categories: value-based [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38], policy-based [39][40][41][42][43][44], or actor-critic [45][46][47][48][49][50]. However, when it comes to generating trading strategies for sin-gle stock, the DRL algorithms primarily adopt value-based approaches.…”

Section: Drl In Financial Tradingmentioning

confidence: 99%

“…Ma et al developed a parallel multi-module DRL algorithm for stock trading, employing multiple neural networks and RL techniques to capture both current market data and long-term historical trends [29]. Li et al utilized a combination of Convolutional Neural Networks (CNN) and LSTM networks with Double DQN and Dueling DQN algorithms to learn optimal dynamic trading strategies from stock data and candlestick charts [33]. Taghian et al proposed a framework that integrated DQN with technical indicators to learn an optimal trading policy for individual assets [34].…”

Section: Drl In Financial Tradingmentioning

confidence: 99%

DADE-DQN: Dual Action and Dual Environment Deep Q-Network for Enhancing Stock Trading Strategy

Huang,

Lu,

Zhou

et al. 2023

Mathematics

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) has attracted strong interest since AlphaGo beat human professionals, and its applications in stock trading are widespread. In this paper, an enhanced stock trading strategy called Dual Action and Dual Environment Deep Q-Network (DADE-DQN) for profit and risk reduction is proposed. Our approach incorporates several key highlights. First, to achieve a better balance between exploration and exploitation, a dual-action selection and dual-environment mechanism are incorporated into our DQN framework. Second, our approach optimizes the utilization of storage transitions by utilizing independent replay memories and performing dual mini-batch updates, leading to faster convergence and more efficient learning. Third, a novel deep network structure that incorporates Long Short-Term Memory (LSTM) and attention mechanisms is introduced, thereby improving the network’s ability to capture essential features and patterns. In addition, an innovative feature selection method is presented to efficiently enhance the input data by utilizing mutual information to identify and eliminate irrelevant features. Evaluation on six datasets shows that our DADE-DQN algorithm outperforms multiple DRL-based strategies (TDQN, DQN-Pattern, DQN-Vanilla) and traditional strategies (B&H, S&H, MR, TF). For example, on the KS11 dataset, the DADE-DQN strategy has achieved an impressive cumulative return of 79.43% and a Sharpe ratio of 2.21, outperforming all other methods. These experimental results demonstrate the performance of our approach in enhancing stock trading strategies.

show abstract

Stock Trading Strategies Based on Deep Reinforcement Learning

Cited by 14 publications

References 39 publications

A Novel Convolutional Neural Networks for Stock Trading Based on DDQN Algorithm

A Novel Convolutional Neural Networks for Stock Trading Based on DDQN Algorithm

Trade Ease With Machine Learning and AWS

DADE-DQN: Dual Action and Dual Environment Deep Q-Network for Enhancing Stock Trading Strategy

Contact Info

Product

Resources

About