通过万次实验分析时序模型模块效果，找出最优组合方案。
TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectiveness
- 在模块层面系统评估时序模型组件的性能
- 10,000+ 实验揭示设计选择与场景的匹配规律
- 提供可直接使用的模型推荐工具，适合工程落地
时序预测在多个领域具有广泛应用。尽管深度学习使预测精度显著提升，但架构和设计组件（如序列分解、归一化）在不同条件下的有效性仍存在争议。现有基准主要从整体层面评估模型，难以解释为何某些设计更优。为此，我们提出 TimeRecipe，一个统一的模块级基准框架，通过超过10,000次实验，在多样化数据集、预测范围和任务设置下系统评估各组件效果。结果表明，对设计空间的充分探索可获得超越现有最先进方法的模型，并揭示设计选择与预测场景之间的有意义关联。此外，我们在 TimeRecipe 中发布了实用工具包，基于实证洞察推荐合适模型架构。基准代码已开源：https://github.com/AdityaLab/TimeRecipe。
原文摘要 · Abstract (English)
Time-series forecasting is an essential task with wide real-world applications across domains. While recent advances in deep learning have enabled time-series forecasting models with accurate predictions, there remains considerable debate over which architectures and design components, such as series decomposition or normalization, are most effective under varying conditions. Existing benchmarks primarily evaluate models at a high level, offering limited insight into why certain designs work better. To mitigate this gap, we propose TimeRecipe, a unified benchmarking framework that systematically evaluates time-series forecasting methods at the module level. TimeRecipe conducts over 10,000 experiments to assess the effectiveness of individual components across a diverse range of datasets, forecasting horizons, and task settings. Our results reveal that exhaustive exploration of the design space can yield models that outperform existing state-of-the-art methods and uncover meaningful intuitions linking specific design choices to forecasting scenarios. Furthermore, we release a practical toolkit within TimeRecipe that recommends suitable model architectures based on these empirical insights. The benchmark is available at: https://github.com/AdityaLab/TimeRecipe.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。