DKformer: A Novel Transformer‐Based Model for Interval‐Valued Crude Oil Price Forecasting
Journal of Forecasting · 2026-04 · 45 (3) · 1020-1035
DOI: 10.1002/for.70070 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Forecasting, online erschienen am 01.12.2025. Verfasst von Chuanmiao Yan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Most deep learning techniques are designed for point‐valued data, while interval‐valued data contain richer information over the same time period, especially during extreme events. To leverage this, we propose DKformer, a novel transformer architecture that models interval data as an inseparable set using the loss function. By combining transformers and loss, DKformer learns complex nonstationary and nonlinear patterns in interval data while accounting for uncertainties and dependencies. Compared to existing interval and point‐based benchmark models, DKformer significantly enhances crude oil price forecast accuracy. Remarkably, it demonstrates robust out‐of‐sample prediction performance across various forecast horizons. Furthermore, the effectiveness of DKformer is preserved even under extreme conditions, including Black Swan events. Our work highlights the potential for DKformer to enhance decision‐making in energy and finance, where robustness to uncertainty and the ability to handle extreme events hold paramount importance.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yan, C., Zhang, X., Cui, R., Sun, Y., & Wang, S. (2026). DKformer: A Novel Transformer‐Based Model for Interval‐Valued Crude Oil Price Forecasting. Journal of Forecasting, 45(3), 1020-1035. https://doi.org/10.1002/for.70070
Vancouver
Yan C, Zhang X, Cui R, Sun Y, Wang S. DKformer: A Novel Transformer‐Based Model for Interval‐Valued Crude Oil Price Forecasting. Journal of Forecasting. 2026;45(3):1020-1035. doi:10.1002/for.70070
BibTeX
@article{Yan2026,
author = {Yan, Chuanmiao and Zhang, Xinyu and Cui, Ruhong and Sun, Yuying and Wang, Shouyang},
title = {DKformer: A Novel Transformer‐Based Model for Interval‐Valued Crude Oil Price Forecasting},
journal = {Journal of Forecasting},
year = {2026},
volume = {45},
number = {3},
pages = {1020--1035},
doi = {10.1002/for.70070}
}
EUVIMED