Google 发布 TimesFM-3 时间序列预测模型
原标题：Google's new AI model predicts the future from sales data, weather, and discount schedules
AI 摘要
Google Research 发布时间序列预测模型 TimesFM-3，基于 Transformer，将 32 个连续数据点打包为一个 patch 并统一归一化，沿时间轴和跨序列两个方向交替处理数据。该模型拥有 3.3 亿参数，在超过一万亿数据点上训练，支持零样本预测，可同时处理多个相关变量、历史已知因素和未来已知事件，并输出九个值以刻画预测的不确定范围。Google 称其在 Gift-Eval、FEV-Bench 和 Time 三个基准上均排名第一，模型已在 GitHub 和 Hugging Face 上发布，并计划未来几周内接入 BigQuery。
正文节选
Google's new AI model predicts the future from sales data, weather, and discount schedules Google Research has released TimesFM-3, an AI model that forecasts the future from time series like daily sales figures, drawing on related data and known upcoming events to improve its predictions. Real-world forecasts rarely depend on a single variable, and Google illustrates this with a retail chain trying to predict ice cream sales. A good forecast should also factor in related products like waffle con