SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies
Fan Zhou, Chen Pan, Lintao Ma, Yu Liu, Shiyu Wang, James Zhang, Xinxin Zhu, Xuanwei Hu
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.
BibTeX
@article{Zhou_Pan_Ma_Liu_Wang_Zhang_Zhu_Hu_Hu_Zheng_Lei_Yun_2023, title={SLOTH: Structured Learning and Task-Based Optimization for Time Series Forecasting on Hierarchies}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26350}, DOI={10.1609/aaai.v37i9.26350}, abstractNote={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.}, number={9}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zhou, Fan and Pan, Chen and Ma, Lintao and Liu, Yu and Wang, Shiyu and Zhang, James and Zhu, Xinxin and Hu, Xuanwei and Hu, Yunhua and Zheng, Yangfei and Lei, Lei and Yun, Hu}, year={2023}, month={Jun.}, pages={11417-11425} }