Cross-Temporal Forecast Reconciliation at Digital Platforms with Machine Learning

TL;DR

This paper introduces a machine learning-based method for producing coherent, high-frequency cross-temporal forecasts for digital platform data, enabling better decision-making across hierarchical levels.

Contribution

It presents a novel non-linear hierarchical forecast reconciliation approach that is fast, automated, and suitable for complex, high-dimensional platform data.

Findings

Effective reconciliation of forecasts across multiple levels.

Applicable to large-scale, real-world streaming datasets.

Supports high-frequency decision-making processes.

Abstract

Platform businesses operate on a digital core and their decision making requires high-dimensional accurate forecast streams at different levels of cross-sectional (e.g., geographical regions) and temporal aggregation (e.g., minutes to days). It also necessitates coherent forecasts across all levels of the hierarchy to ensure aligned decision making across different planning units such as pricing, product, controlling and strategy. Given that platform data streams feature complex characteristics and interdependencies, we introduce a non-linear hierarchical forecast reconciliation method that produces cross-temporal reconciled forecasts in a direct and automated way through the use of popular machine learning methods. The method is sufficiently fast to allow forecast-based high-frequency decision making that platforms require. We empirically test our framework on unique, large-scale streaming datasets from a leading on-demand delivery platform in Europe and a bicycle sharing system in New York City.