Deep Deterministic Policy Gradient based portfolio management system
AbstractThe Deep Reinforcement Learning Process (DRL) has made considerable progress since its inception towards the production of various independent systems. Nowadays, deep learning gives Reinforcement Learning (RL) the ability to conform to several dysfunctions that were previously difficult, if not impossible to resolve. In this paper, we explore the power of Deep Reinforcement Learning in order to solve the problem of portfolio management which is a process that allows the selection, prioritization and management of funds by following a defined policy. Our objective is to obtain an optimal strategy to maximize the expected return while minimizing the costs. To do this, we use the Deep Deterministic Policy Gradient which is an off-policy algorithm adapted for environments with continuous action spaces. The obtained results demonstrate that the model achieves a higher rate of return than the strategy of “Uniform Buy and Hold” stocks and the strategy of “Buy Best Stock in last month”.
The submitting author warrants that the submission is original and that she/he is the author of the submission together with the named co-authors; to the extend the submission incorporates text passages, figures, data or other material from the work of others, the submitting author has obtained any necessary permission.
Articles in this journal are published under the Creative Commons Attribution Licence (CC-BY). This is to get more legal certainty about what readers can do with published articles, and thus a wider dissemination and archiving, which in turn makes publishing with this journal more valuable for you, the authors.
In order for iJIST to publish and disseminate research articles, we need publishing rights. This is determined by a publishing agreement between the author and iJIST.
By submitting an article the author grants to this journal the non-exclusive right to publish it. The author retains the copyright and the publishing rights for his article without any restrictions.
The names and email addresses entered in this journal site will be used exclusively for the stated purposes of this journal and will not be made available for any other purpose or to any other party.