This study examines the predictability of three major cryptocurrencies—bitcoin, ethereum, and litecoin—and the profitability of trading strategies devised upon machine learning techniques (e.g., linear models, random forests, and support vector machines). The models are validated in a period characterized by unprecedented turmoil and tested in a period of bear markets, allowing the assessment of whether the predictions are good even when the market direction changes between the validation and test periods. The classification and regression methods use attributes from trading and network activity for the period from August 15, 2015 to March 03, 2019, with the test sample beginning on April 13, 2018. For the test period, five out of 18 individual models have success rates of less than 50%. The trading strategies are built on model assembling. The ensemble assuming that five models produce identical signals (Ensemble 5) achieves the best performance for ethereum and litecoin, with annualized Sharpe ratios of 80.17% and 91.35% and annualized returns (after proportional round-trip trading costs of 0.5%) of 9.62% and 5.73%, respectively. These positive results support the claim that machine learning provides robust techniques for exploring the predictability of cryptocurrencies and for devising profitable trading strategies in these markets, even under adverse market conditions.

In December 2017, the CBOE and CME launched bitcoin futures, arguing that, similar to other futures, these contracts would provide more price transparency, price discovery, and a risk management tool for bitcoin. Using daily data from several sources, this paper investigates the hedging properties of CBOE Bitcoin futures during these initial months of trading. The results point out that bitcoin futures are effective hedging instruments not only for bitcoin, but also for other cryptocurrencies. Bitcoin futures can even cope with bitcoin tail risk, however they may leverage the existence of extreme losses for other currencies.

We analyze the path from cryptocurrencies to official Central Bank Digital Currencies (CBDCs), to shed some light on the ultimate dematerialization of money. To that end, we made an extensive search that resulted in a review of more than 100 academic and grey literature references, including official positions from central banks. We present and discuss the characteristics of the different CBDC variants being considered—namely, wholesale, retail, and, for the latter, the account-based, and token-based—as well as ongoing pilots, scenarios of interoperability, and open issues. Our contribution enables decision-makers and society at large to understand the potential advantages and risks of introducing CBDCs, and how these vary according to many technical and economic design choices. The practical implication is that a debate becomes possible about the trade-offs that the stakeholders are willing to accept.

This paper investigates the information transmission between the most important cryptocurrencies - Bitcoin, Litecoin, Ripple, Ethereum and Bitcoin Cash. We use a VAR modelling approach, upon which the Geweke’s feedback measures and generalized impulse response functions are computed. This methodology allows us to fully characterize the direction, intensity and persistence of information flows between cryptocurrencies. At this data granularity, most of information transmission is contemporaneous. However, it seems that there are some lagged feedback effects, mainly from other cryptocurrencies to Bitcoin. The generalized impulse-response functions confirm that there is a strong contemporaneous correlation and that there is not much evidence of lagged effects. The exception appears to be related to the overreaction of Bitcoin returns to contemporaneous shocks.

This paper suggests a new approach for portfolio choice. In this framework, the investor, with CRRA preferences, has two objectives: the maximization of the expected utility and the minimization of the portfolio expected illiquidity. The CRRA utility is measured using the portfolio realized volatility, realized skewness and realized kurtosis, while the portfolio illiquidity is measured using the well-known Amihud illiquidity ratio. Therefore, the investor is able to make her choices directly in the expected utility/liquidity (EU/L) bi-dimensional space. We conduct an empirical analysis in a set of fourteen stocks of the CAC 40 stock market index, using high frequency data for the time span from January 1999 to December 2005 (seven years). The robustness of the proposed model is checked according to the out-of-sample performance of different EU/L portfolios relative to the minimum variance and equally weighted portfolios. For different risk aversion levels, the EU/L portfolios are quite competitive and in several cases consistently outperform those benchmarks, in terms of utility, liquidity and certainty equivalent.