Conformal Prediction for Time Series with Transformer

We present a conformal prediction method for time series using Transformer. Specifically, we use Transformer decoder as a conditional quantile estimator to predict the quantiles of prediction residuals, which are used to estimate prediction interval. We hypothesize that Transformer decoder benefits the estimation of prediction interval by learning temporal dependencies across past prediction residuals. Our comprehensive experiments using simulated and real data empirically demonstrate the superiority of the proposed method compared to the existing state-of-the-art conformal prediction methods.