Method

The full method, published.

Bayesian media mix modeling and learned multi-touch attribution, fit on your own data. It refreshes nightly, refits weekly, and every figure carries its interval.

The pipeline

From weekly rows to a published number.

Every fit passes through the same six stages. Two of them are checks: one on your data before a fit starts, one on the fit before it is published. When a check stops a fit, you see why.

  1. 01 Ingest

    Weekly rows are the source of truth: one revenue column and one column per channel, from a connected source or a weekly file. Touchpoints and conversions land beside them in the same schema.

  2. 02 Resolve

    Identifiers resolve to subjects your organization owns. Suppression and erasure are built in, so every person-level row has a lawful basis.

  3. 03 Check the data

    Too few weeks, too little variation, a missing revenue column or a gap in the sequence is reported before a fit starts. Modeling begins when the data qualifies.

  4. 04 Fit

    The media mix model refits weekly, with carryover and saturation estimated per channel from your data. With more than 60 weeks of history, it is first fit without the last eight weeks and scored on them.

  5. 05 Pass the standard

    A fit is published only when it reconciles to booked revenue, credits media with something, and converges. Otherwise you get the reason and the fix.

  6. 06 Report

    Every figure carries its interval, and the next dollar's return is ranked by channel. The simulator, the revenue graph and the forecast all read this same fit.

The output

What a fit reports.

A response curve for every channel, with its credible band. Read across it and you know what the channel returned, and what its next dollar will.

Response curves · adstock and saturation fitted per channel

Marginal return on next dollar

Paid search3.4×
Microsoft Ads3.1×
Paid social2.1×

This ordering, not the average, is what should drive reallocation.

  1. 01Baseline share

    How much revenue comes from everything that is not media, with its interval.

  2. 02Channel contribution

    Each channel's share of modeled revenue over the fit window. Never a point without a width.

  3. 03Carryover and saturation

    How long each channel's effect lasts and where it flattens, estimated from your rows, not a benchmark.

  4. 04The next dollar

    Return on the next dollar by channel, ranked, so a reallocation has a reason before it has a slide.

The standard

What a fit has to pass.

Three conditions stand between a fit and your plan. When one is not met, the page names it and says what to change in the data.

It reconciles to booked revenue

The channels' modeled contribution can never add up to more than the revenue you actually booked. A fit that claims credit for money that doesn't exist is held back.

It credits media with something

When the model hands every dollar to baseline, it has learned nothing about your channels, usually because spend barely moved. You see that, and how to vary spend so the next fit can learn.

Its chains agree

A Bayesian fit runs several chains that have to land in the same place. Until they do, no single figure is shown, however confident it looks.

Model card

Written down for your data team.

Priors, the carryover and saturation forms, the data thresholds and how each fit is scored. Nothing about how a number was produced is hidden.

OutcomeWeekly booked revenue
CarryoverGeometric adstock, up to 8 weeks, per channel
SaturationLogistic response curve, per channel
SeasonalityYearly, with 52 or more weeks
Minimum data52 weeks; 104 recommended
HoldoutLast 8 weeks, with more than 60 weeks of history
Uncertainty80% credible interval on every figure

Principles

Four rules the model keeps.

Ranges, not points

A contribution without an interval is a guess with a confident face. Every figure shows its width.

Your rows, every night

Models are fit to your organization's own data, refreshed nightly and refit weekly. Never to a demo dataset.

One fit, every page

The simulator reads the response curves, the revenue graph draws the fit, and the forecast projects it. No page quotes a number another disagrees with.

Documented, start to finish

Priors, functional forms and per-fit diagnostics are published, so your data team can check the work.

Read the method. Then plan on it.

Early access is by application. We set up each team ourselves.