Insurance pricing systems should fulfill the auto-calibration property to ensure that there is no systematic cross-financing between different price cohorts in the pricing system. Often, regression models are not auto-calibrated. We present the method of isotonic recalibration to a given regression model which gives us the auto-calibration property. As a nice side result we see that under a low signal-to-noise ratio, this isotonic recalibration step leads to explainable pricing systems because the resulting isotonically recalibrated regression functions have a low complexity.