[2603.02906] Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach

Computer Science > Machine Learning arXiv:2603.02906 (cs) [Submitted on 3 Mar 2026] Title:Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach Authors:Bo Liu, Shao-Bo Lin, Changmiao Wang, Xiaotong Liu View a PDF of the paper titled Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach, by Bo Liu and 3 other authors View PDF HTML (experimental) Abstract:Time series forecasting enables early warning and has driven asset performance management from traditional planned maintenance to predictive maintenance. However, the lack of interpretability in forecasting methods undermines users' trust and complicates debugging for developers. Consequently, interpretable time-series forecasting has attracted increasing research attention. Nevertheless, existing methods suffer from several limitations, including insufficient modeling of temporal dependencies, lack of feature-level interpretability to support early warning, and difficulty in simultaneously achieving the accuracy and interpretability. This paper proposes the interpretable polynomial learning (IPL) method, which integrates interpretability into the model structure by explicitly modeling original features and their interactions of arbitrary order through polynomial representations. This design preserves temporal dependencies, provides feature-level interpretability, and offers a flexible trade-off between prediction accuracy and interpretability by adju...