IDEA: Interpretable Dynamic Ensemble Architecture for Time Series Prediction

TL;DR

The paper introduces IDEA, an interpretable dynamic ensemble architecture that improves time series prediction accuracy and generalization through explainable, independently predicting base learners with sparse communication, achieving state-of-the-art results.

Contribution

The paper presents a novel ensemble architecture for time series prediction that is interpretable, dynamically adaptable, and achieves superior accuracy compared to existing benchmarks.

Findings

Forecast accuracy improves by 2.6% over statistical benchmarks on TOURISM dataset.

Forecast accuracy improves by 2% over deep learning benchmarks on M4 dataset.

Architecture is robust, explainable, and applicable across various domains.

Abstract

We enhance the accuracy and generalization of univariate time series point prediction by an explainable ensemble on the fly. We propose an Interpretable Dynamic Ensemble Architecture (IDEA), in which interpretable base learners give predictions independently with sparse communication as a group. The model is composed of several sequentially stacked groups connected by group backcast residuals and recurrent input competition. Ensemble driven by end-to-end training both horizontally and vertically brings state-of-the-art (SOTA) performances. Forecast accuracy improves by 2.6% over the best statistical benchmark on the TOURISM dataset and 2% over the best deep learning benchmark on the M4 dataset. The architecture enjoys several advantages, being applicable to time series from various domains, explainable to users with specialized modular structure and robust to changes in task distribution.