Follow us
Publications Commentary Research People Events News Resources and Videos About IFS
Home Publications Exact and robust conformal inference methods for predictive machine learning with dependent data

Exact and robust conformal inference methods for predictive machine learning with dependent data

Cemmap Working Paper CWP16/18

We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including  block structures in the permutation scheme. As a result, the proposed method retains the exact, model-free validity when the data are i.i.d. or more generally exchangeable, similar to usual conformal inference methods. When exchangeability fails, as is the case for common time series data, the proposed approach is approximately valid under weak assumptions on the conformity score.