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

Victor Chernozhukov, Kaspar Wüthrich, Yinchu Zhu

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.

MoreLess

Year of publication:	[2018]
Authors:	Chernozhukov, Victor ; Wüthrich, Kaspar ; Zhu, Yinchu
Publisher:	[London] : Cemmap, Centre for Microdata Methods and Practice, The Institute for Fiscal Studies, Department of Economics, UCL
Subject:	Conformal inference \| permutation and randomization \| dependent data \| groups \| Künstliche Intelligenz \| Artificial intelligence \| Induktive Statistik \| Statistical inference \| Prognoseverfahren \| Forecasting model \| Schätztheorie \| Estimation theory \| Zeitreihenanalyse \| Time series analysis