This research study compares alternative daily cryptocurrency volatility targets constructed from a common Binance intraday source under a unified and quality-controlled data pipeline. The analysis considers both realized-return-based and range-based measures, including intraday realized variance, calendar-boundary-augmented realized variance, and a realized-range proxy. Forecasting performance is evaluated using direct heterogeneous autoregressive (HAR) models at the 1-, 7-, and 30-day horizons on common out-of-sample support under two complementary loss functions: quasi-likelihood (QLIKE) and log-scale mean squared error. The results show that no universal winner emerges across these criteria. The calendar-boundary-augmented realized variance delivers the best average performance under QLIKE at all horizons, whereas the realized-range proxy performs best under log-scale mean squared error and exhibits greater month-by-month stability. By contrast, classical daily range estimators such as Garman–Klass and Parkinson are not competitive relative to the leading alternatives in this sample. A secondary Bitcoin-conditioned robustness analysis suggests that relative target rankings may vary across market conditions, with stronger contrasts during stress-like episodes. Overall, the findings indicate that the preferred daily volatility target depends primarily on the forecasting objective and should therefore be treated as a substantive empirical choice in cryptocurrency volatility forecasting rather than as a secondary implementation detail.
Lin et al. (Mon,) studied this question.