Transformer Conformal Prediction for Time Series

TL;DR

This paper introduces a Transformer-based conformal prediction method for time series that effectively captures long-range dependencies to produce accurate prediction intervals, outperforming existing methods.

Contribution

It proposes using a Transformer decoder as a conditional quantile estimator within conformal prediction for time series, enhancing interval estimation accuracy.

Findings

Outperforms state-of-the-art conformal prediction methods

Demonstrates effectiveness on simulated and real data

Improves prediction interval accuracy for long-range dependencies

Abstract

We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the quantiles of prediction residuals, which are used to estimate the prediction interval. We hypothesize that the Transformer decoder benefits the estimation of the 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.