Conformal Prediction Algorithms for Time Series Forecasting: Methods and Benchmarking

TL;DR

This paper reviews and benchmarks conformal prediction methods tailored for time series forecasting, addressing challenges posed by temporal dependencies and evaluating their performance on real-world data.

Contribution

It provides a comprehensive survey and benchmarking of conformal prediction algorithms adapted for time series, highlighting the most effective approaches for uncertainty quantification.

Findings

Multi-step split conformal prediction achieves 90% coverage.

The method demonstrates superior efficiency compared to alternatives.

Benchmarking on a large dataset validates the effectiveness of the proposed approaches.

Abstract

Reliable uncertainty quantification is of critical importance in time series forecasting, yet traditional methods often rely on restrictive distributional assumptions. Conformal prediction (CP) has emerged as a promising distribution-free framework for generating prediction intervals with rigorous theoretical guarantees. However, applying CP to sequential data presents a primary challenge: the temporal dependencies inherent in time series fundamentally violate the core assumption of data exchangeability, upon which standard CP guarantees are built. This paper critically examines the main categories of algorithmic solutions designed to address this conflict. We survey and benchmark methods that relax the exchangeability assumption, those that redefine the data unit to be a collection of independent time series, approaches that explicitly model the dynamics of the prediction residuals, and online learning algorithms that adapt to distribution shifts to maintain long-run coverage. We use AutoARIMA as the base forecaster on a large-scale monthly sales dataset, evaluating marginal coverage, interval width, and the Winkler score. Our benchmark results show that multi-step split conformal prediction method meets the 90% coverage threshold and demonstrates the best efficiency.