Local vs. Global Models for Hierarchical Forecasting

TL;DR

This paper compares local and global models for hierarchical time series forecasting, showing that global models leveraging cross-series information outperform local models in accuracy and efficiency.

Contribution

It introduces and evaluates new global forecasting models based on LightGBM that outperform traditional local models and methods like ES and ARIMA.

Findings

Global models achieve higher accuracy than local models.

Global models are more computationally efficient.

LightGBM-based models outperform traditional methods.

Abstract

Hierarchical time series forecasting plays a crucial role in decision-making in various domains while presenting significant challenges for modelling as they involve multiple levels of aggregation, constraints, and availability of information. This study explores the influence of distinct information utilisation on the accuracy of hierarchical forecasts, proposing and evaluating locals and a range of Global Forecasting Models (GFMs). In contrast to local models, which forecast each series independently, we develop GFMs to exploit cross-series and cross-hierarchies information, improving both forecasting performance and computational efficiency. We employ reconciliation methods to ensure coherency in forecasts and use the Mean Absolute Scaled Error (MASE) and Multiple Comparisons with the Best (MCB) tests to assess statistical significance. The findings indicate that GFMs possess significant advantages for hierarchical forecasting, providing more accurate and computationally efficient solutions across different levels in a hierarchy. Two specific GFMs based on LightGBM are introduced, demonstrating superior accuracy and lower model complexity than their counterpart local models and conventional methods such as Exponential Smoothing (ES) and Autoregressive Integrated Moving Average (ARIMA).