CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yao, Fulong, Zhao, Wanqing, Zheng, Chao, Han, Xiaofei
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911262484463616
author Yao, Fulong
Zhao, Wanqing
Zheng, Chao
Han, Xiaofei
author_facet Yao, Fulong
Zhao, Wanqing
Zheng, Chao
Han, Xiaofei
contents Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaReTS, a novel multi-task learning framework that combines classification and regression tasks for multi-step time series forecasting problems. The framework adopts a dual-stream architecture, where a classification branch learns the stepwise trend into the future, while a regression branch estimates the corresponding deviations from the latest observation of the target variable. The dual-stream design provides more interpretable predictions by disentangling macro-level trends from micro-level deviations in the target variable. To enable effective learning in output prediction, deviation estimation, and trend classification, we design a multi-task loss with uncertainty-aware weighting to adaptively balance the contribution of each task. Furthermore, four variants (CaReTS1--4) are instantiated under this framework to incorporate mainstream temporal modelling encoders, including convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and Transformers. Experiments on real-world datasets demonstrate that CaReTS outperforms state-of-the-art (SOTA) algorithms in forecasting accuracy, while achieving higher trend classification performance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting
Yao, Fulong
Zhao, Wanqing
Zheng, Chao
Han, Xiaofei
Machine Learning
Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics. This paper proposes CaReTS, a novel multi-task learning framework that combines classification and regression tasks for multi-step time series forecasting problems. The framework adopts a dual-stream architecture, where a classification branch learns the stepwise trend into the future, while a regression branch estimates the corresponding deviations from the latest observation of the target variable. The dual-stream design provides more interpretable predictions by disentangling macro-level trends from micro-level deviations in the target variable. To enable effective learning in output prediction, deviation estimation, and trend classification, we design a multi-task loss with uncertainty-aware weighting to adaptively balance the contribution of each task. Furthermore, four variants (CaReTS1--4) are instantiated under this framework to incorporate mainstream temporal modelling encoders, including convolutional neural networks (CNNs), long short-term memory networks (LSTMs), and Transformers. Experiments on real-world datasets demonstrate that CaReTS outperforms state-of-the-art (SOTA) algorithms in forecasting accuracy, while achieving higher trend classification performance.
title CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting
topic Machine Learning
url https://arxiv.org/abs/2511.09789