CRYPTO PORTFOLIO OPTIMIZATION THROUGH LENS OF TAIL RISK AND VARIANCE MEASURES

Abstract

The choice of an adequate risk measure in portfolio optimization depends to a large extent on the characteristics and dynamics of the underlying assets. For investors and asset managers, a range of potential market risks provides much- needed insights into the optimization of their portfolio of assets. Since this paper focuses on multiple risk measures, it presents the investors with a better insight into the potential magnitude of the risk they are faced with. Since the risk-reward optimization target can be adjusted for a broad choice of risk measures in this paper we will test the performance of the classical risk measure i.e. standard deviation versus a tail risk measure such as expected tail loss (ETL). Our goal is to find which of the two offers the better performance for a portfolio of cryptocurrencies and if the differences are statistically significant. The setup for our analysis is testing two optimization targets (MinVar and MinETL) on 10 portfolios of cryptocurrencies randomly chosen from a sample of 70 cryptocurrencies with the highest market capitalization.

Keywords

• portfolio optimization
• cryptocurrency
• risk evaluation
• investments