Bayesian Hidden Markov Models for Cryptocurrency Return Regimes

Summary

The study uses multi-state hidden Markov models to forecast and explain returns for Bitcoin, Ether, and Ripple. It compares model types, including a non-homogeneous hidden Markov specification, and examines financial, economic, and cryptocurrency-specific predictors. The non-homogeneous model with four states delivers the strongest one-step-ahead predictive performance among the models considered for all three assets.

The authors attribute the gains over a single-regime random walk to latent states capturing periods with different return behavior. For Bitcoin, the reported states distinguish bullish, bearish, and calm conditions; for Ether and Ripple, they separate periods by profit and risk characteristics. The analysis also finds that predictor relationships can differ across hidden states and may be linear or nonlinear. These are empirical findings for the selected cryptocurrencies, models, and sample; the description gives no sample dates or detailed performance measures, so it does not establish that the results generalize to other assets or future periods.

Key ideas

• Multi-state hidden Markov models represent cryptocurrency returns as changing across latent regimes.
• A four-state non-homogeneous model has the best one-step-ahead forecasting performance among the tested models.
• The latent states reflect differing return characteristics in Bitcoin, Ether, and Ripple.
• Predictor effects can vary by state and can be linear or nonlinear.
• The reported evidence is specific to the assets and models examined.

Tags

# Exploring the Predictability of Cryptocurrencies via Bayesian Hidden Markov Models


# Exploring the Predictability of Cryptocurrencies via Bayesian Hidden Markov Models









In this paper, we consider a variety of multi-state Hidden Markov models for predicting and explaining the Bitcoin, Ether and Ripple returns in the presence of state (regime) dynamics. In addition, we examine the effects of several financial, economic and cryptocurrency specific predictors on the cryptocurrency return series. Our results indicate that the Non-Homogeneous Hidden Markov (NHHM) model with four states has the best one-step-ahead forecasting performance among all competing models for all three series. The dominance of the predictive densities over the single regime random walk model relies on the fact that the states capture alternating periods with distinct return characteristics. In particular, the four state NHHM model distinguishes bull, bear and calm regimes for the Bitcoin series, and periods with different profit and risk magnitudes for the Ether and Ripple series. Also, conditionally on the hidden states, it identifies predictors with different linear and non-linear effects on the cryptocurrency returns. These empirical findings provide important insight for portfolio management and policy implementation.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.