AnalyticsBudget, forecasting and MMMIntermediateBuilds a checklist

Marketing-mix-modelling readiness and data-requirements checklist

Assesses whether you have the data and conditions for an MMM, lists what to collect, and warns about what a model can and cannot tell you.

For: Performance marketers, Marketing analysts, Growth marketers · Works with: Any capable chat model (ChatGPT, Claude, Gemini, others)

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Act as a marketing-mix-modelling consultant. Assess whether a mid-size online furniture retailer is ready for a media-mix model and what to prepare. What I have: daily revenue, daily spend by channel for 18 months, promo calendar. History length: 18 months. Channels: paid search, paid social, affiliates, email, TV (regional). Spend variability (do budgets change meaningfully over time?): paid social changes monthly; TV only ran twice. Known events and promotions: Black Friday, spring sale, a stock-out in June. Outcome variable: weekly revenue. Deliver: 1. A readiness verdict with reasons (ready, nearly ready, not yet), framed as an assessment of data sufficiency, not a guarantee. 2. A data-requirements table: variable, grain (daily or weekly), source, issues to check (missing values, definition changes, outliers). 3. The factors that make MMM unreliable (too little history, collinear channels, little spend variation, structural breaks, tiny channels) and how each applies to me. 4. Which questions an MMM can answer for me (aggregate channel contribution and saturation) and which it cannot (user-level journeys, creative-level effects), in plain language. 5. How to combine MMM with experiments for calibration, as an option to consider. 6. A short project plan (data prep, build or buy, validation, decision use) without cost or timeline claims. 7. List missing information. Rules: do not invent model outputs, ROI numbers or benchmarks. State assumptions; if information is missing or not provided, ask. Check that the table lists only variables relevant to my channels. Treat any model result as an estimate with uncertainty, not proof of causation.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

Who you are.

What is available.

How long.

Channels in the model.

How spend varies.

Known events.

What you model.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

A readiness verdict with reasons, a data-requirements table, the reliability risks that apply (for example little TV variation), what MMM can and cannot answer, a calibration suggestion and a short plan. (Illustrative.)

Expected format: Verdict, data table, risks, capabilities, calibration option, plan.

How to use it

  1. Share with whoever will build the model.
  2. Collect missing data first.
  3. Calibrate with experiments where possible.

Limitations

  • MMM requires sufficient history and spend variation; many small businesses cannot support it.
  • Results are estimates with wide uncertainty.

Platform notes

Any capable chat model (ChatGPT, Claude, Gemini, others)

Official docs read · checked 2026-10-11

Works in any capable chat model. Paste a small anonymised sample and recompute the key numbers yourself: chat models can misread columns or miscalculate, and they cannot run your statistical tests reliably.

General notes on Any capable chat model (ChatGPT, Claude, Gemini, others)
  • These prompts are plain text and work in any chat assistant. For analytics prompts, paste a small, anonymised export; a chat model can misread columns or miscalculate, so recompute key numbers yourself.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID ana-036. We will correct or remove it.

Related prompts

  • AnalyticsAdvancedDesigns a test

    Incrementality test design: holdout or geo experiment

    Designs an incrementality test plan with hypotheses, units, duration decisions and pre-registered success criteria, without inventing sample sizes.

    Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    Budget reallocation scenarios with saturation caveats

    Builds transparent what-if scenarios for moving budget between channels, with simple assumptions about diminishing returns clearly labelled.

    Any capable chat model (ChatGPT, Claude, Gemini, others) · Google Sheets / Excel