Nowadays, Artificial Intelligence (AI) is changing our daily life in many application fields. Automatic trading has inspired a large number of field experts and scientists in developing innovative techniques and deploying cutting-edge technologies to trade different markets. In this context, cryptocurrency has given new interest in the application of AI techniques for predicting the future price of a financial asset. In this work Deep Reinforcement Learning is applied to trade bitcoin. More precisely, Double and Dueling Double Deep Q-learning Networks are compared over a period of almost four years. Two reward functions are also tested: Sharpe ratio and profit reward functions. The Double Deep Q-learning trading system based on Sharpe ratio reward function demonstrated to be the most profitable approach for trading bitcoin.

Lucarelli, G., Borrotti, M. (2019). A Deep Reinforcement Learning Approach for Automated Cryptocurrency Trading. In IFIP Advances in Information and Communication Technology (pp.247-258). Springer New York LLC [10.1007/978-3-030-19823-7_20].

A Deep Reinforcement Learning Approach for Automated Cryptocurrency Trading

Borrotti, M
2019

Abstract

Nowadays, Artificial Intelligence (AI) is changing our daily life in many application fields. Automatic trading has inspired a large number of field experts and scientists in developing innovative techniques and deploying cutting-edge technologies to trade different markets. In this context, cryptocurrency has given new interest in the application of AI techniques for predicting the future price of a financial asset. In this work Deep Reinforcement Learning is applied to trade bitcoin. More precisely, Double and Dueling Double Deep Q-learning Networks are compared over a period of almost four years. Two reward functions are also tested: Sharpe ratio and profit reward functions. The Double Deep Q-learning trading system based on Sharpe ratio reward function demonstrated to be the most profitable approach for trading bitcoin.
slide + paper
Automatic trading; Cryptocurrency; Deep Reinforcement Learning; Double Deep Q-learning Networks; Dueling architecture;
Automatic trading; Cryptocurrency; Deep Reinforcement Learning; Double Deep Q-learning Networks; Dueling architecture
English
15th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2019
2019
IFIP Advances in Information and Communication Technology
9783030198220
2019
559
247
258
http://www.springer.com/series/6102
none
Lucarelli, G., Borrotti, M. (2019). A Deep Reinforcement Learning Approach for Automated Cryptocurrency Trading. In IFIP Advances in Information and Communication Technology (pp.247-258). Springer New York LLC [10.1007/978-3-030-19823-7_20].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/234877
Citazioni
  • Scopus 19
  • ???jsp.display-item.citation.isi??? ND
Social impact