GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

TL;DR

GMP-AR introduces a novel message-passing and adaptive reconciliation framework that enhances temporal hierarchy forecasting accuracy and coherence, demonstrated on real-world datasets and applied to payment traffic management.

Contribution

It proposes a new GMP-AR framework combining message passing and adaptive reconciliation to improve forecast accuracy and coherence in temporal hierarchies.

Findings

Outperforms state-of-the-art methods on real-world datasets.

Maintains coherence without sacrificing forecasting accuracy.

Successfully applied to payment traffic management in Alipay.

Abstract

Time series forecasts of different temporal granularity are widely used in real-world applications, e.g., sales prediction in days and weeks for making different inventory plans. However, these tasks are usually solved separately without ensuring coherence, which is crucial for aligning downstream decisions. Previous works mainly focus on ensuring coherence with some straightforward methods, e.g., aggregation from the forecasts of fine granularity to the coarse ones, and allocation from the coarse granularity to the fine ones. These methods merely take the temporal hierarchical structure to maintain coherence without improving the forecasting accuracy. In this paper, we propose a novel granularity message-passing mechanism (GMP) that leverages temporal hierarchy information to improve forecasting performance and also utilizes an adaptive reconciliation (AR) strategy to maintain coherence without performance loss. Furthermore, we introduce an optimization module to achieve task-based targets while adhering to more real-world constraints. Experiments on real-world datasets demonstrate that our framework (GMP-AR) achieves superior performances on temporal hierarchical forecasting tasks compared to state-of-the-art methods. In addition, our framework has been successfully applied to a real-world task of payment traffic management in Alipay by integrating with the task-based optimization module.