A Deep Multimodal Reinforcement Learning System Combined with CNN and LSTM for Stock Trading

Shin, Hong-Gi; Ra, Ilkyeun; Choi, Yong-Hoon

doi:10.1109/ictc46691.2019.8939991

Cited by 16 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features extracted through the CNN layer were divided into column vectors and inputted to the LSTM layer. The reinforcement learning defined the agents' policy neural network structure, reward, and action and provided buying, selling, and holding probabilities as final output [77]. Jia, W. proposed a reinforcement learning with an LSTM-based agent that could automatically sense the dynamics of the stock market and could alleviate the difficulty of manually designing indicators from massive data.…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…Table 20 shows the details of the papers that used the Sharpe ratio as a performance metric. In this table, papers [14,18] used a CNN-based model; papers [71,75] used a DNN-based model; papers [77] and [82] used a reinforcement learning-based model; and papers [84,88,90,91] used other deep learning methods. It could be found that papers [75,84,91] performed best, which used a DNN model, and Sharpe ratio was in the range of 5-10.…”

Section: Analysis Based On Sharpe Ratiomentioning

confidence: 99%

“…The features extracted through the CNN layer were divided into column vectors and inputted to the LSTM layer. The reinforcement learning defines agents' policy neural network structure, reward, and action, and provides buying, selling, and holding probabilities as final output [58].…”

Section: Cnnmentioning

confidence: 99%

“…Multiple articles selected 5. Sharpe ratio and return rate, we could find that paper [58] had a much higher Sharpe ratio than paper [63]; paper [62] had a higher return rate than paper [59] then followed by the paper [60].…”

Section: Reinforcement Learningmentioning

confidence: 99%

“…Table 20 showed the details of the papers' that used the Sharpe ratio as a preformance metric. In this table, paper [11] and [15] used CNN based model; paper [50], [89] used DNN based model; paper [58], [63] used Reinforcement learning-based model, and paper [65], [69], [72], [74] used other deep learning method.…”

Section: Analysis Based On Sharpe Ratiomentioning

confidence: 99%

See 4 more Smart Citations

A Survey of Forex and Stock Price Prediction Using Deep Learning

Zhao

Khushi

2021

ASI

212

View full text Add to dashboard Cite

Predictions of stock and foreign exchange (Forex) have always been a hot and profitable area of study. Deep learning applications have been proven to yield better accuracy and return in the field of financial prediction and forecasting. In this survey, we selected papers from the Digital Bibliography & Library Project (DBLP) database for comparison and analysis. We classified papers according to different deep learning methods, which included Convolutional neural network (CNN); Long Short-Term Memory (LSTM); Deep neural network (DNN); Recurrent Neural Network (RNN); Reinforcement Learning; and other deep learning methods such as Hybrid Attention Networks (HAN), self-paced learning mechanism (NLP), and Wavenet. Furthermore, this paper reviews the dataset, variable, model, and results of each article. The survey used presents the results through the most used performance metrics: Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Mean Square Error (MSE), accuracy, Sharpe ratio, and return rate. We identified that recent models combining LSTM with other methods, for example, DNN, are widely researched. Reinforcement learning and other deep learning methods yielded great returns and performances. We conclude that, in recent years, the trend of using deep-learning-based methods for financial modeling is rising exponentially.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%