Surrogate Modeling for Explainable Predictive Time Series Corrections

TL;DR

This paper presents a local surrogate method for making time-series forecasting models more interpretable by analyzing the differences in model parameters after error correction, aiding understanding of underlying data patterns.

Contribution

It introduces a novel local surrogate approach that enhances explainability of time-series correction models by interpreting parameter differences after error removal.

Findings

Demonstrates the method's ability to uncover underlying data patterns

Provides illustrative examples of explainability in forecasting

Shows potential for improving interpretability of complex models

Abstract

We introduce a local surrogate approach for explainable time-series forecasting. An initially non-interpretable predictive model to improve the forecast of a classical time-series 'base model' is used. 'Explainability' of the correction is provided by fitting the base model again to the data from which the error prediction is removed (subtracted), yielding a difference in the model parameters which can be interpreted. We provide illustrative examples to demonstrate the potential of the method to discover and explain underlying patterns in the data.