Abstract
This study investigated the performance of a trading agent based on a convolutional neural network model in portfolio management. The results showed that with real-world data the agent could produce relevant trading results, while the agent’s behavior corresponded to that of a high-risk taker. The data used were wide in comparison with earlier reported research and was based on the full set of the S&P 500 stock data for twenty-one years supplemented with selected financial ratios. The results presented are new in terms of the size of the data set used and with regards to the model used. The results provide direction and offer insight into how deep learning methods may be used in constructing automatic trading systems.
Highlights
Efficient and profitable portfolio management is one of the key functions of the financial industry and is on the top of the list of things that investors are looking for when making investments
We acknowledge that the choice of using only three model architectures limits the reliability of the results; we feel that for the purposes of this research it is sufficient
This paper explored the applicability of machine learning models to active portfolio management using models based on deep reinforcement learning
Summary
Efficient and profitable portfolio management is one of the key functions of the financial industry and is on the top of the list of things that investors are looking for when making investments. In vein with the above, the key idea of this research is to concentrate on how portfolio management can be aided by the use of modern business analytics, namely, by using an artificial neural network (ANN)-based system to automatically detect market anomalies by technical analysis and to exploit them to maximize portfolio returns by realizing excess returns. Previous academic literature on portfolio management with ANN-based systems [17,18,19,20] have shown promising results, but the reported research has so far used relatively small data sets and the focus has primarily been on comparatively demonstrating the abilities of different system and/or algorithm architectures. For a technical introduction to reinforcement learning and artificial neural networks, we refer the reader to [23]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
