Google Research 发布 TimesFM 3.0 预测模型
AI 总结
Google Research 发布 TimesFM 3.0,支持原生单变量与多变量时间序列预测,并可使用仅历史及历史加未来的动态协变量。项目提供 google/timesfm-3.0-pytorch PyTorch 检查点,仓库还介绍了面向 Apple 芯片的 MLX 后端。报告中的三项基准排名为厂商声明,尚未得到独立验证。
深度见解
TimesFM 3.0 以多变量预测和协变量支持扩展了 Google Research 的时间序列基础模型,但下载权重仅限非商业、非生产用途。
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/
TimesFM
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.