Reinforcement learning applied to Forex trading

Carapuço, João; Neves, Rui; Horta, Nuno

doi:10.1016/j.asoc.2018.09.017

Cited by 87 publications

(46 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It also adopted various action strategies that used Q-values to analyse profitable actions within a confused market, defined as a financial market with no clear direction or movement [22]. Another adoption of Q-learning algorithm with neural networks was completed by Carapuço et al in 2018 [23]. Three hidden layers were used in the neural networks trained under the Q-learning algorithm with the Rectified Linear Unit as the activation function [23].…”

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%

“…Another adoption of Q-learning algorithm with neural networks was completed by Carapuço et al in 2018 [23]. Three hidden layers were used in the neural networks trained under the Q-learning algorithm with the Rectified Linear Unit as the activation function [23]. Moody et al in 2001 showed that over the six month test period for the USD/GBP exchange rate, the recurrent reinforcement learning trading system achieved a 15% return and a Sharpe ratio of 2.3 after annualization [6].…”

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%

“…The overall profit on the Standard & Poor's 500 index was increased by 4.5 times compared with the baseline reinforcement model [22]. The adoption of the Q-learning algorithm by Carapuço et al in 2018 eventually was able to make profitable trades based on out-of-sample data despite the difficulties presented by the lack of data predictability within the simulated foreign exchange market [23]. The algorithm was tested on the EUR/USD foreign exchange market over a period of 8 years of data from 2010 to 2017 using 10 tests of different initial conditions with an overall yearly average profit of over 15% [23].…”

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%

“…The adoption of the Q-learning algorithm by Carapuço et al in 2018 eventually was able to make profitable trades based on out-of-sample data despite the difficulties presented by the lack of data predictability within the simulated foreign exchange market [23]. The algorithm was tested on the EUR/USD foreign exchange market over a period of 8 years of data from 2010 to 2017 using 10 tests of different initial conditions with an overall yearly average profit of over 15% [23]. It also appeared that the learning rate in the training dataset was stable and the model could be used for profitable trading [23].…”

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%

“…The algorithm was tested on the EUR/USD foreign exchange market over a period of 8 years of data from 2010 to 2017 using 10 tests of different initial conditions with an overall yearly average profit of over 15% [23]. It also appeared that the learning rate in the training dataset was stable and the model could be used for profitable trading [23].…”

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%

See 4 more Smart Citations

Reinforcement Learning in Financial Markets

Meng

Khushi

2019

Data

105

View full text Add to dashboard Cite

Recently there has been an exponential increase in the use of artificial intelligence for trading in financial markets such as stock and forex. Reinforcement learning has become of particular interest to financial traders ever since the program AlphaGo defeated the strongest human contemporary Go board game player Lee Sedol in 2016. We systematically reviewed all recent stock/forex prediction or trading articles that used reinforcement learning as their primary machine learning method. All reviewed articles had some unrealistic assumptions such as no transaction costs, no liquidity issues and no bid or ask spread issues. Transaction costs had significant impacts on the profitability of the reinforcement learning algorithms compared with the baseline algorithms tested. Despite showing statistically significant profitability when reinforcement learning was used in comparison with baseline models in many studies, some showed no meaningful level of profitability, in particular with large changes in the price pattern between the system training and testing data. Furthermore, few performance comparisons between reinforcement learning and other sophisticated machine/deep learning models were provided. The impact of transaction costs, including the bid/ask spread on profitability has also been assessed. In conclusion, reinforcement learning in stock/forex trading is still in its early development and further research is needed to make it a reliable method in this domain.Google Scholar was used to search for the reinforcement learning articles for this systematic review. By typing into Google Scholar the key phrases "reinforcement learning forex" and "reinforcement learning stock trading" and then all the results were filtered according to the selection process given below in Figure 1. The search results returned from Google Scholar was automatically sorted by relevance, therefore only the first few pages are selected for manual inspection for eligibility. Afterwards, the results of the searched phrases were manually inspected without opening the article links to determine the most relevant articles for this systematic review. The selected articles from this step were then opened and their content read through to determine the final list of articles to be reviewed. Of 27 articles reviewed, 20 articles implemented or simulated trades to maximise profit and 7 articles were only interested in forecasting future financial asset prices. Of 20 trading articles 11 articles provided comparison with other models and 10 did not.

show abstract

Section: Recurrent Neural Network and Q Learning Combinedmentioning

confidence: 99%