Interpreting uninterpretable predictors: kernel methods, Shtarkov solutions, and random forests

Abstract

Many of the best predictors for complex problems are typically regarded as hard to interpret physically. These include kernel methods, Shtarkov solutions, and random forests. We show that, despite the inability to interpret these three predictors to infinite precision, they can be asymptotically approximated and admit conceptual interpretations in terms of their mathematical/statistical properties. The resulting expressions can be in terms of polynomials, basis elements, or other functions that an analyst may regard as interpretable.