Google's new AI model predicts the future from sales data, weather, and discount schedules

Google Research has released TimesFM-3, a 330-million-parameter model designed to forecast time series data by incorporating external variables such as weather patterns and promotional schedules. Unlike traditional methods that calculate data points sequentially, this model generates predictions for entire future periods in a single step. By integrating diverse contextual inputs, the tool aims to improve accuracy for businesses managing complex logistics and demand planning.