Working · 2026-11Vendor claimGrowth opsPaid

Open-source marketing mix modeling

Use open-source MMM tools to estimate each channel's contribution and saturation without relying only on click attribution.

Also called: MMM

Claim and evidence

The claimUse open-source MMM tools to estimate each channel's contribution and saturation without relying only on click attribution.

No dated example yet. Treat this tactic as a hypothesis.

What the numbers show

No published number for this tactic has passed our word-for-word check yet, so there is no chart.

Why it works

Diagram, not data
Weekly spend bychannelWeekly conversionsLift-test resultsOpen-source mix modelBudget moves alongsaturation curves
Weekly spend bychannelWeeklyconversionsLift-test resultsOpen-source mix modelBudget moves along saturationcurves

Statistical models fit aggregate spend to outcomes, giving a view that does not need user-level tracking and can be calibrated against experiments.

How to run it

  1. Collect weekly spend and conversions by channel
  2. Run Robyn or Meridian
  3. Calibrate with lift tests
  4. Reallocate budget based on saturation curves
  5. Re-fit quarterly

Ways to run it

Design options to test, not promised results.

  1. Option AModel plus calibration

    Fit the model on aggregate data and calibrate it with lift or geo tests before trusting channel estimates.

  2. Option BSaturation-led reallocation

    Move budget away from channels that the curves show as saturated toward ones with headroom.

  3. Option CQuarterly re-fit

    Refresh the model each quarter and compare recommended budget moves with the previous run.

Dated examples

No dated example yet. Treat this tactic as a hypothesis.

Does it still work?

Workingas of 2026-11

Both tools are active open-source projects; pages undated. source

Risks

  • Needs enough history and channel variation
  • Model assumptions can mislead

Sources

  1. developers.google.com · Google for Developers · undated
    “Meridian is an open-source MMM built by Google that provides innovative solutions to key measurement challenges.”
    ✓ quote checked word-for-word on the page
  2. github.com · GitHub (Meta Robyn) · undated
    “Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science.”
    ○ page blocks automated checks; quote as relayed

Change log

  • 2026-11-20 — harvest v0.1 (acq-paid)