A study on Ensemble Learning for Time Series Forecasting and the need for Meta-Learning

TL;DR

This paper explores ensemble learning methods for time series forecasting across diverse datasets, demonstrating their benefits and proposing a meta-learning approach to select optimal ensemble configurations for each dataset.

Contribution

Introduces ensemble methods for time series forecasting and proposes a meta-learning step to select the best ensemble strategy based on dataset features.

Findings

Ensembles improve forecasting accuracy across datasets.

No single ensemble strategy is universally best.

Meta-learning helps tailor ensemble choices to specific datasets.

Abstract

The contribution of this work is twofold: (1) We introduce a collection of ensemble methods for time series forecasting to combine predictions from base models. We demonstrate insights on the power of ensemble learning for forecasting, showing experiment results on about 16000 openly available datasets, from M4, M5, M3 competitions, as well as FRED (Federal Reserve Economic Data) datasets. Whereas experiments show that ensembles provide a benefit on forecasting results, there is no clear winning ensemble strategy (plus hyperparameter configuration). Thus, in addition, (2), we propose a meta-learning step to choose, for each dataset, the most appropriate ensemble method and their hyperparameter configuration to run based on dataset meta-features.