A comprehensive analysis of Bitcoin volatility forecasting using time-series econometric models

The world of cryptocurrency has expanded rapidly over the last ten years, with the most recent advancements witnessed in the last few years as many individuals have realized the importance of storing digital assets online. According to Twitter statistics, there are roughly 1500 tweets on Bitcoin alone per hour, which lends credence to this claim. As a consequence, investors are eager to learn how to make profitable cryptocurrency trades and investments, and the fundamental idea behind digital currencies is growing in acceptance and understanding. This study investigates the notable inefficiencies in the several research efforts that have attempted to create algorithms that can accurately forecast price fluctuations in the Bitcoin market. This work compares different econometric models based on Root Mean Squared Error (RMSE) and Root Mean Squared Percentage Error (RMSPE). The RMSE score of our proposed Threshold Autoregressive Conditional Heteroskedasticity (TARCH) model is 0.065, and an RMSPE score of 0.197, which is minimal compared to other models. The proposed Bootstrap TARCH technique appropriate for simulating the intricate and volatile characteristics of Bitcoin returns.