The essential idea is that a “conformity function” exists. Effectively you are constructing a sort of multivariate cumulative distribution function for your machine learning gizmo using the conformity function. Such CDFs exist for classical stuff like ARIMA and linear regression under the correct circumstances; CP brings the idea to machine learning in general, and to models like ARIMA when the standard parametric confidence intervals won’t work.
Hmm. Introductions in [Vovk, Gammerman, and Shafer (2005);ShaferTutorial2008]. Modern takes in see (“Predicting With Confidence: Using Conformal Prediction in Drug Discovery” 2021; Zeni, Fontana, and Vantini 2020). Question: how well does this work under dataset shift? (Tibshirani et al. 2019).