Google's TimesFM-3 predicts sales with discounts, weather, and related products
Google Research has released TimesFM-3, an AI model that forecasts future sales and other time series data by drawing on related variables and known upcoming events. For sales teams and revenue planners, the model's ability to factor in planned promotions, weather forecasts, and complementary product sales could sharpen demand predictions that directly affect inventory and staffing decisions.
Real-world forecasts rarely depend on a single variable. Google illustrates this with a retail chain trying to predict ice cream sales. A good forecast should also factor in related products like waffle cones or syrup, along with past foot traffic, weather, discount campaigns, and holidays.
How TimesFM-3 handles multiple data streams
TimesFM-3 is built on a Transformer, the same base architecture as its predecessors, but it groups 32 consecutive data points into a single patch and normalizes each series to a common scale. This lets measurements of very different magnitudes be compared directly.
The model processes data in two alternating directions. Along the time axis, it looks for patterns within a single series, only drawing on past values to avoid leaking future information. Across series, it compares all variables at a given point in time and learns how they relate. That lets it pick up on effects like how a discount on one product affects sales of another.
The model has 330 million parameters and was trained on real and synthetic time series totaling more than one trillion data points, according to Google. Like its predecessors, it works zero-shot and needs no extra training for new tasks.
Known future events improve accuracy
TimesFM-3 handles three types of supplementary data. It predicts multiple related variables at once, like different ice cream flavors. It incorporates factors known only for the past, such as historical foot traffic. It also uses known future events like planned discounts or weather forecasts. Instead of a single point estimate, TimesFM-3 outputs nine values per time step to capture the range and uncertainty of each prediction.
Earlier versions predicted the future one block at a time, which Google said was slow, compute-heavy, and let errors compound as each prediction built on the last. TimesFM-3 marks all future time steps as blanks and fills them in a single pass.
Google shows the payoff with its ice cream example. A model that only knows past sales just continues the usual weekly pattern, blind to planned promotions. When TimesFM-3 gets the discount schedule, it learns from history how much promotions boost demand and expects roughly 20 percent more units on each promotion day.
Benchmark results and availability
On Gift-Eval, FEV-Bench, and Time, TimesFM-3 ranks first among all pretrained forecasting models in both point accuracy and uncertainty calibration, according to Google. Competitors include Amazon's Chronos-2, the Toto-2.0 family, and Google's own TimesFM-2.5. Even limited to a single variable, TimesFM-3 matches or beats the field, and adding more data widens the gap.
TimesFM-3 is available on GitHub and Hugging Face, and Google plans to add it to BigQuery in the coming weeks. TimesFM-2.5 currently handles single-variable forecasting there via the AI.FORECAST command.
Since the family launched in 2024, Google said it has been deployed in retail, finance, manufacturing, healthcare, and the sciences. All versions through TimesFM-2.5, released in September 2025, could only process one data series at a time, making TimesFM-3's multivariate support a major step forward.
Why this matters for sales professionals
Sales teams that plan promotions, manage territory quotas, or allocate inventory across product lines can test whether a multivariate forecasting model reduces the gap between predicted and actual demand. The ability to feed planned discount schedules into a forecast means you can estimate the lift from a promotion before running it, then compare that estimate against the actual result. For teams already using AI for Sales in pipeline or lead scoring, adding time series forecasting to the stack is a natural next step. If your organization runs on BigQuery, the upcoming integration means you won't need separate infrastructure to experiment with it. Sales operations and revenue leaders who want to build this capability internally can start with AI for Sales Representatives training to understand how these models fit into existing workflows.
Your membership also unlocks:
