This study examines the regime-dependent behaviour of Bitcoin prices using a Gaussian Hidden Markov Model. Using daily Bitcoin data, the analysis identifies three distinct latent market regimes: a bullish regime with positive returns and moderate volatility, a stable regime with low volatility and weak returns, and a bearish regime with negative returns and heightened volatility. The findings further show that bullish and bearish regimes are relatively persistent, while the stable regime is more transitional. These results suggest that Bitcoin price dynamics are not constant over time but evolve through recurring shifts in market conditions. By capturing these nonlinear patterns, the Gaussian Hidden Markov Model provides a useful framework for understanding the structure, volatility, and predictability of Bitcoin markets. The study highlights the value of regime-based modelling for analysing cryptocurrency behaviour, especially in emerging economies where exposure to digital asset risks is increasing.

Keywords: Bitcoin, Gaussian Hidden Markov Model, Regime-switching, Price Volatility, Cryptocurrency Markets