DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to forecast several related series with drivers with Timesfm

Give TimesFM 3.0 multiple target variates plus past only and past and future covariates in one call.

Short answer: Install it with pip install timesfm[torch]; then Shape your targets as a 2D array of (num_variates, context_length) as the README shows; Pass past_only_covariates and past_future_covariates to predict_batch alongside contexts and horizon. All steps.

platform. The 3.0 weights are non-commercial; production use goes through Google Cloud services per the README.

Who it is forA planner whose demand depends on price, weather or promotions.

The problemUnivariate models ignore the drivers you already know.

The outcomeA joint forecast across all target variates, with quantiles.

What you need first

  • Python with pip, and `pip install timesfm[torch]`, or `pip install timesfm[mlx]` on Apple silicon
  • A CUDA GPU for the PyTorch examples, which set device to cuda
  • Your series as NumPy arrays

Steps

  1. Install it with pip install timesfm[torch]
  2. Shape your targets as a 2D array of (num_variates, context_length) as the README shows
  3. Pass past_only_covariates and past_future_covariates to predict_batch alongside contexts and horizon
  4. Check that outputs[0].forecast has shape (num_variates, horizon) and quantiles adds the nine deciles

Prompt for your agent

With google-research/timesfm, forecast <my three product series> for 24 steps using my known promotions as a past and future covariate, and report the median and the 10th and 90th percentiles.

Caveat. Past and future covariates must cover context plus horizon, as in the README shapes.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for google-research/timesfm and "Forecast several related series with drivers"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer