{"ID":2843040,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09789","arxiv_id":"2511.09789","title":"CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.09789","url_pdf":"https://arxiv.org/pdf/2511.09789v1","authors":"[\"Fulong Yao\",\"Wanqing Zhao\",\"Chao Zheng\",\"Xiaofei Han\"]","published":"2025-11-12T22:43:40Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}