This work introduces a data-driven framework for rate control and applies it to high frequency (HF) communication systems that propagate via the Earth’s ionosphere. The rate control approach uses statistical techniques to forecast channel state with an autoregressive (AR) model, which has previously been applied to different forms of wireless fading, including "medium" timescale fading at HF. The objective of rate control is to maximize the data rate while constraining the rate of packets decoded in error. We show that under ideal assumptions, the rate controller selects the rate by backing off from the forecast average signal-to-noise ratio (SNR) by a factor of sigmaQ^-1(Beta), where sigma^2 correlates with fading variance, Beta denotes a constraint on decoder errors, and Q(.) is the complementary cumulative distribution function of the Gaussian distribution. Simulation results on an HF channel model show that compared with naive schemes, AR forecasting provides a good balance between achieving high rate and ensuring reliability.