PatchDecomp: Interpretable Patch-Based Time Series Forecasting

TL;DR

PatchDecomp is a neural network method for time series forecasting that combines high accuracy with interpretability by attributing predictions to specific input patches, including exogenous variables.

Contribution

It introduces a patch-based approach that enhances interpretability without sacrificing forecasting accuracy in neural network models.

Findings

Achieves comparable accuracy to state-of-the-art methods.

Provides clear patch-wise attribution for interpretability.

Enables visualization of contributions for qualitative insights.

Abstract

Time series forecasting, which predicts future values from past observations, plays a central role in many domains and has driven the development of highly accurate neural network models. However, the complexity of these models often limits human understanding of the rationale behind their predictions. We propose PatchDecomp, a neural network-based time series forecasting method that achieves both high accuracy and interpretability. PatchDecomp divides input time series into subsequences (patches) and generates predictions by aggregating the contributions of each patch. This enables clear attribution of each patch, including those from exogenous variables, to the final prediction. Experiments on multiple benchmark datasets demonstrate that PatchDecomp provides predictive performance comparable to recent forecasting methods. Furthermore, we show that the model's explanations not only influence predicted values quantitatively but also offer qualitative interpretability through visualization of patch-wise contributions.