JudgeCast：基于经验信息协变量判断的时间序列预测

中文摘要 AI 辅助

协变量效应因情境而异并随时间变化，这要求预测者评估如何在每个预测情境中使用它们。随着预测的进行，先前预测的观测值变得可用，为后续预测提供了关于过去协变量使用的反馈。然而，当多个协变量共同作用时，预测误差仅揭示与观测值的数值差异，而无法说明协变量本应如何使用。我们提出了JudgeCast，一个基于经验的时间序列预测框架，用于处理带协变量的预测。遵循判断性调整实践，冻结的TSFM提供基础预测，而冻结的LLM利用当前情境和相关经验对其进行调整。在调整过程中，评估协变量效应和确定数值调整扮演着不同的角色，因此JudgeCast首先形成显式的逐协变量判断，然后确定调整量。在观测之后，JudgeCast利用基础预测的观测残差来重构替代判断，并通过它们产生的调整结果来评估原始判断和替代判断。表现最佳的决策被选中并保留为验证过的经验，用于后续预测。在多个多样化的真实世界数据集上，JudgeCast优于强基线模型。消融实验表明，显式的逐协变量判断可以改进预测时的调整，而残差引导的经验构建相比保留原始决策作为经验，能带来更可靠的预测增益。

英文摘要

Covariate effects vary across contexts and shift over time, requiring forecasters to assess how to use them for each forecasting context. As forecasting proceeds, observations for earlier forecasts become available, providing feedback on past covariate use for subsequent forecasts. However, when multiple covariates act together, the forecast error reveals the numerical discrepancy from the observation but not how the covariates should have been used. We introduce JudgeCast, an experience-based framework for time series forecasting with covariates. Following the judgmental adjustment practice, a frozen TSFM provides the base forecast, while a frozen LLM uses the current context and relevant experience to adjust it. Within the adjustment, assessing covariate effects and determining the numerical adjustment serve distinct roles, so JudgeCast first forms explicit covariate-wise judgments and then determines the adjustment. After observation, JudgeCast uses the observed residual of the base forecast to reconstruct alternative judgments and evaluates the original and alternatives through their resulting adjustments. The best-performing decision is selected and retained as validated experience for subsequent forecasts. Across diverse real-world datasets, JudgeCast outperforms strong baselines. Ablations show that explicit covariate-wise judgment can improve forecast-time adjustment, while residual-guided experience construction yields more reliable forecasting gains than retaining raw decisions as experience.

发表机构

• Yonsei University（延世大学）
• Konkuk University（建国大学）

机构由 AI 辅助整理，请以论文原文为准。