Using Deep Learning Conditional Value-at-Risk Based Utility Function in Cryptocurrency Portfolio Optimisation

Abstract

One of the critical risks associated with cryptocurrency assets is the so-called downside risk, or tail risk. Conditional Value-at-Risk (CVaR) is a measure of tail risks that is not normally considered in the construction of a cryptocurrency portfolio. In this paper, we propose a new approach to portfolio construction based on a deep learning CVaR utility function. This approach is designed to address the issue of tail risk. We evaluate the performance of this approach in comparison to other portfolio construction techniques, including the naïve, minimum variance and mean-variance portfolios. Our findings indicate that the proposed approach outperforms traditional optimisation models.