Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning

Taghian, Mehran; Asadi, Ahmad; Safabakhsh, Reza

doi:10.48550/arxiv.2010.14194

Cited by 2 publications

(6 citation statements)

References 29 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on these results, we use the vanilla Deep Q-learning algorithm (Mnih et al, 2013) as our baseline algorithm. As our choice of the neural network architecture, we follow Taghian et al (2020) who compare different feature extraction neural network architectures for the task of DRL for financial asset trading. Based on tests on four assets, the authors find that, overall, a simple multi-layer-perceptron architecture based on a Deep Q-learning algorithm performs the best.…”

Section: Related Workmentioning

confidence: 99%

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

Pigorsch¹,

Schäfer²

2021

Preprint

View full text Add to dashboard Cite

This paper proposes a Deep Reinforcement Learning algorithm for financial portfolio trading based on Deep Q-learning (Mnih et al., 2013). The algorithm is capable of trading high-dimensional portfolios from cross-sectional datasets of any size which may include data gaps and non-unique history lengths in the assets. We sequentially set up environments by sampling one asset for each environment while rewarding investments with the resulting asset's return and cash reservation with the average return of the set of assets. This enforces the agent to strategically assign capital to assets that it predicts to perform above-average. We apply our methodology in an out-of-sample analysis to 48 US stock portfolio setups, varying in the number of stocks from ten up to 500 stocks, in the selection criteria and in the level of transaction costs. The algorithm on average outperforms all considered passive and active benchmark investment strategies by a large margin using only one hyperparameter setup for all portfolios.

show abstract

Section: Related Workmentioning

confidence: 99%

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

Pigorsch¹,

Schäfer²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the proposed model, the decoder part is a target or policy network used in the deep Q-Learning based model proposed by [4] to learn trading strategies.…”

Section: Decodermentioning

confidence: 99%

“…In recent years, machine learning (ML) models and deep neural networks (DNNs) have been widely used for learning profitable investment strategies in both single asset trading and portfolio management problems [3]. Among the techniques used for learning asset-specific trading rules, genetic programming (GP) and deep reinforcement learning (DRL) methods have been more interesting for the research community [4].…”

Section: Introductionmentioning

confidence: 99%

“…For single stocks trading, Wang et al [16] employed deep Q-learning to build an end-to-end deep Q-trading system for learning trading strategies. [4] studied the DRL performance in learning single asset-specific trading rules and concluded that: 1) the quality of extracted features from the input can greatly affect the performance of the learned strategy by DRL models, and 2) proposing a good feature extractor from a long-term historical price data sequence would obviously improve the profitability of the resulting trading strategy. Considering the results from [4], proposing a model to learn good features from a long-term price sequence would effectively contribute to improve the performance of DRL models.…”

Section: Introductionmentioning

confidence: 99%

“…Considering the results reported by [4], we combined the encoder-decoder framework with the DRL techniques and proposed an end-to-end model to learn informative features from a long-term price sequence of a specific financial instrument and learn a profitable trading strategy. The encoder-decoder framework is one of the state-of-the-art neural structures applied in tasks requiring extracting complex feature representation, specially in cases that the input is presented in the form of a long-term time-series [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Reinforcement Learning Based Encoder-Decoder Framework for Learning Stock Trading Rules

Taghian,

Asadi,

Safabakhsh

2021

Preprint

Self Cite

View full text Add to dashboard Cite

A wide variety of deep reinforcement learning (DRL) models have recently been proposed to learn profitable investment strategies. The rules learned by these models outperform the previous strategies specially in high frequency trading environments. However, it is shown that the quality of the extracted features from a long-term sequence of raw prices of the instruments greatly affects the performance of the trading rules learned by these models. Employing a neural encoder-decoder structure to extract informative features from complex input time-series has proved very effective in other popular tasks like neural machine translation and video captioning in which the models face a similar problem.The encoder-decoder framework extracts highly informative features from a long sequence of prices along with learning how to generate outputs based on the extracted features. In this paper, a novel end-to-end model based on the neural encoder-decoder framework combined with DRL is proposed to learn single instrument trading strategies from a long sequence of raw prices of the instrument.The proposed model consists of an encoder which is a neural structure responsible for learning informative features from the input sequence, and a decoder which is a DRL model responsible for learning profitable strategies based on the features extracted by the encoder. The parameters of the encoder and the decoder structures are learned jointly, which enables the encoder to extract features fitted to the task of the decoder DRL.

show abstract

Learning Financial Asset-Specific Trading Rules via Deep Reinforcement Learning

Cited by 2 publications

References 29 publications

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning

A Reinforcement Learning Based Encoder-Decoder Framework for Learning Stock Trading Rules

Contact Info

Product

Resources

About