[PDF]

Machine learning for cryptocurrency trading


Nicolo Licata

16/05/2023

Supervised by Yuhua Li; Moderated by Yazmin Ibanez Garcia

Algorithmic automatic trading has always been a hot topic, and it has been studied for a long time. With the development of science and technology, new research results in algorithmic automatic trading emerge. Supervised deep learning and deep reinforcement learning are typical methods. Many researchers proposed many similar or different algorithmic automatic trading with supervised deep learning or deep reinforcement learning. In 2020, Lei, K., Zhang, B., Li, Y., Yang, M. and Shen, Y. proposed a framework called time-driven feature-aware jointly deep reinforcement learning model (TFJ-DRL), and made a great success. Besides, there are still some works that can be done based on their work. This project aims to build on existing works to develop a framework suitable for automatic trading of cryptocurrency.

Reference: Lei, K., Zhang, B., Li, Y., Yang, M. and Shen, Y. 2020. Time-driven feature-aware jointly deepreinforcementlearningforfinancialsignalrepresentationandalgorithmictrading. Expert Systems with Applications140, p. 112872. doi: 10.1016/j.eswa.2019.112872.


Initial Plan (06/02/2023) [Zip Archive]

Final Report (16/05/2023) [Zip Archive]

Publication Form