On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models

📄 arXiv: 2610.13676v1 📥 PDF

作者: Alexander Kreusel, Maximilian Beichter, Alexandra Nikoltchovska, Benjamin Schäfer, Ralf Mikut, Frederik Zahn, Veit Hagenmeyer

分类: cs.LG

发布日期: 2026-10-09


💡 一句话要点

提出日历特征编码方法以提升时间序列模型预测精度

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 时间序列模型 日历特征 编码方法 预测准确性 协变量支持 SHAP分析 模型比较

📋 核心要点

  1. 现有方法对日历特征的编码处理不足,未能充分考虑其对时间序列预测的影响。
  2. 本研究系统比较了七种日历编码方法,探讨其对时间序列模型预测准确性的影响。
  3. 实验结果显示,编码选择显著影响预测精度,假期的MASE差异高达83%,且不同模型表现差异明显。

📝 摘要(中文)

时间序列基础模型(TSFMs)日益支持协变量,其中日历信息是最常见的分类协变量。然而,如何编码这些特征往往被视为实现细节,而非研究对象。本研究表明,信息在模型中的传播方式显著影响TSFMs的预测准确性。我们系统比较了七种日历编码方法,发现编码选择对所有模型的预测准确性都有影响,假期的MASE差异高达83%。这些发现表明,当前的协变量信息TSFMs基准可能会因固定编码策略而扭曲模型比较。

🔬 方法详解

问题定义:本论文旨在解决日历特征编码对时间序列基础模型预测准确性影响的问题。现有方法往往忽视了编码方式的选择,导致模型性能未能得到充分发挥。

核心思路:论文通过系统比较七种不同的日历编码方法,探讨其在多种时间序列模型中的表现,强调编码方式对预测结果的重要性。

技术框架:研究采用了四种最先进的TSFMs,并在九个受社会活动影响的数据集上进行零-shot滚动评估。主要模块包括数据预处理、编码方法选择、模型训练与评估。

关键创新:论文的创新点在于系统性地比较了传统的目标无关编码(如序数、独热和循环编码)与目标编码的效果,揭示了编码选择对模型性能的显著影响。

关键设计:在实验中,采用了SHAP基于归因分析的方法,评估协变量相对于自回归成分的贡献,并分析了某些编码组合为何会降低模型性能。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果显示,编码选择对所有模型的预测准确性均有显著影响,假期的MASE差异高达83%。此外,某些模型的编码组合在非假期预测中也表现出提升,表明日历信息在时间序列预测中的重要性。

🎯 应用场景

该研究的潜在应用领域包括金融市场预测、气象预报和供应链管理等时间序列分析场景。通过优化日历特征的编码方式,可以显著提升预测模型的准确性,进而为决策提供更可靠的支持。未来,这一研究成果可能推动更多领域对时间序列模型的应用与发展。

📄 摘要(原文)

Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariate in practice, as it is available for every point in time. However, how these features are encoded is largely treated as an implementation detail rather than as an object of study, despite encoding being one of the few design choices left for pretrained models at inference time. With the present study, we demonstrate that the way information is propagated into the model substantially affects forecast accuracy of TSFMs. Therefore, we systematically compare seven calendar encodings, including three conventional target-agnostic representations (ordinal, one-hot, and cyclic) and four target encodings, across four state-of-the-art TSFMs on nine datasets from multiple domains in a zero-shot rolling evaluation. The nine datasets are influenced by social activities, such as weekends and holidays, making calendar information particularly relevant for forecasting. We find that encoding choice affects forecast accuracy across all models, with MASE differences of up to 9.9 % on non-holidays and 83 % on holidays within a single model. Effectiveness and utilization vary substantially across models. Improvements are concentrated around holidays, where calendar information provides signals unavailable from target history, while some model encoding combinations also improve non-holiday forecasts. A SHAP-based attribution analysis locates the contribution of the covariates relative to the autoregressive component and explains why some model-encoding combinations degrade performance. Our findings suggest that current benchmarks for covariate-informed TSFMs can distort model comparisons by imposing fixed encoding strategies.