AIThe New Stack4 days ago
Google launches TimesFM-3 multivariate forecasting model
4 min read
Google Research introduced TimesFM-3, a 330-million-parameter time series foundation model natively pre-trained for multivariate forecasting on over 1 trillion time points. It generates the entire forecasting horizon in a single forward pass and predicts nine quantiles per target series.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyGoogle
Summary by ByteBrief
