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

Google has launched TimesFM-3, a forecasting model that analyzes time series data alongside related information and known future events like sales promotions or weather forecasts. The model, featuring 330 million parameters, fills in all future time points in a single pass, significantly reducing compute time and minimizing compounding errors. This model marks a significant advancement in improving forecasting accuracy, making it a valuable tool for executives in sectors like retail, where precise predictions can influence business strategies.