时间序列基础模型预测准不代表因果效应估计准
From Forecasting to World Modeling: Can Temporal Foundation Models Recover Causal Response?
做定价或销量分析的朋友值得看看：论文用真实零售数据证明，TabPFN 这类基础模型预测准但因果效应估计可能全错，连工具变量用错形式还会更糟。需要从预测走向因果决策的团队建议读一下。
一篇 arXiv 论文系统评估了已发布的表格和时间序列基础模型，以及一个专门预训练用于估计因果效应的基础模型，核心问题是：预测准确是否意味着能恢复价格变化对销量的因果响应？研究在模拟数据（真实效应已知）和真实零售销售记录上展开验证。
论文报告三个发现：第一，预测精度与价格效应预测的准确性不相关，即使模型能把销量预测得很准，对价格弹性的估计仍可能严重偏差；第二，对表格基础模型而言，提供更多上下文信息能改善预测，但不能改善价格效应的估计；第三，计量经济学的标准工具——工具变量，只有以特定形式输入时才能降低误差，若以原始形式提供，在存在混杂因素时反而会放大所有模型的误差。
这项工作说明零售、定价决策等场景不能只看 forecast 指标选模型，做因果推断仍需专门的处理流程。对需要在基础模型上叠加因果分析的企业数据团队，这是一份有操作意义的评估参考。
From Forecasting to World Modeling: Can Temporal Foundation Models Recover Causal Response?
A model that forecasts sales accurately can still mislead a retailer about how sales respond to a price change. We evaluate released tabular and time-series foundation models, as well as a foundation model pretrained specifically to estimate causal effects. We report three findings. First, forecast accuracy does not indicate the accuracy of the predicted effect of price, both on simulated data in which the true effect is known and on real retail sales records. Second, for the tabular foundation models, additional context improves forecasts but not the predicted effect of price. Third, instrumental variables, the standard remedy in econometrics, reduce this error only when supplied in a specific form and increase it for every model under confounding when supplied as raw instruments.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include 时间序列, 因果推断, 基础模型, 工具变量.
Source attribution: curated from arXiv cs.LG (@Juwon Hong, Minha Hwang, Venkatesh Shankar).
