SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

TL;DR

This paper introduces a novel hierarchical time series forecasting method that integrates hierarchical information during prediction and employs neural optimization networks for flexible, constraint-based reconciliation, improving accuracy and real-world applicability.

Contribution

It proposes two tree-based feature integration mechanisms and neural optimization networks that enhance hierarchical forecasting accuracy and flexibility without strong assumptions.

Findings

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

Achieves coherence without assumptions using neural networks

Effectively incorporates hierarchical info during forecasting

Abstract

Multivariate time series forecasting with hierarchical structure is widely used in real-world applications, e.g., sales predictions for the geographical hierarchy formed by cities, states, and countries. The hierarchical time series (HTS) forecasting includes two sub-tasks, i.e., forecasting and reconciliation. In the previous works, hierarchical information is only integrated in the reconciliation step to maintain coherency, but not in forecasting step for accuracy improvement. In this paper, we propose two novel tree-based feature integration mechanisms, i.e., top-down convolution and bottom-up attention to leverage the information of the hierarchical structure to improve the forecasting performance. Moreover, unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only,we utilize deep neural optimization networks, which not only achieve coherency without any assumptions, but also allow more flexible and realistic constraints to achieve task-based targets, e.g., lower under-estimation penalty and meaningful decision-making loss to facilitate the subsequent downstream tasks. Experiments on real-world datasets demonstrate that our tree-based feature integration mechanism achieves superior performances on hierarchical forecasting tasks compared to the state-of-the-art methods, and our neural optimization networks can be applied to real-world tasks effectively without any additional effort under coherence and task-based constraints