AnalyticsAttribution, incrementality and testsIntermediateAnalyses your data

Attribution model comparison: why platform, GA4 and backend disagree

Compares channel credit under several attribution views from your table and explains the differences, without declaring a winner.

For: Performance marketers, Marketing analysts, Growth marketers · Works with: Any capable chat model (ChatGPT, Claude, Gemini, others), Google Analytics 4

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 measurement analyst. Compare channel credit under different attribution views using ONLY the table below for Q3 2026. Data (channel | conversions under view A | view B | view C | spend): Channel | Last-click | Data-driven | Platform-reported | Spend Paid search | 520 | 480 | 610 | 30000 Paid social | 160 | 260 | 540 | 24000 Email | 300 | 280 | n/a | 2000 Direct | 400 | 330 | n/a | 0 Views: A = GA4 last-click; B = GA4 data-driven; C = ad-platform self-reported (windows differ). Conversion definition: purchase. Tasks: 1. State assumptions (including whether conversions are deduplicated across views, and whether totals reconcile; check this and report). 2. Compute each channel's share of credit under each view and the change versus last-click (or the view I name), from the data only, and verify. 3. Explain, in plain language, why each channel's credit differs between views, using general attribution mechanics (credit allocation, windows, view-through, cross-device, consent loss). 4. Say which decisions each view is more suited for as a reasoned suggestion, and where it could mislead. 5. Describe what would help settle the question (holdout or geo experiments, incrementality tests, MMM), and what each can and cannot answer. 6. List missing data. Rules: do not invent numbers or declare one view the truth. If data is missing or not provided, say so. Attribution models allocate credit; they do not prove causation. Verify arithmetic.

Customize

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

Period.

Paste your table. The default is small fictional sample data so the preview works; replace it with your own.

What view A is.

What view B is.

What view C is.

Shared definition.

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 reconciliation check, share-of-credit by view and change versus last-click, plain-language reasons for differences, which decisions each view suits, experiments that could settle it and missing data. (Illustrative.)

Expected format: Assumptions, credit table, explanations, decision guidance, experiment options.

How to use it

  1. Document each view's settings.
  2. Use views for different questions.
  3. Run experiments for budget-shifting decisions.

Limitations

  • No attribution model measures incrementality.
  • Cross-source totals rarely reconcile.

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.

Google Analytics 4

Official docs read · checked 2026-10-11

GA4 exports and the interface can differ (sampling, thresholds, attribution, data freshness); state which one your numbers came from.

General notes on Google Analytics 4
  • The BigQuery export has daily events_YYYYMMDD tables and intraday tables; intraday lacks some fields, and late-arriving data can update a daily table for up to 3 days.
  • Exported data and the GA4 interface can differ; the export documentation links to separate comparison articles that we did not read.

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-033. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateAnalyses your data

    Reconcile GA4 conversions with ad-platform conversions

    Explains why GA4 and an ad platform report different conversions, by listing likely definitional causes and the checks to confirm each one.

    Google Analytics 4 · Google Ads · Meta Ads +1

  • 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

    A/B test result evaluation with statistical guardrails

    Interprets an A/B test from raw counts with checks for sample-ratio mismatch, peeking and practical significance, without inventing a significance result.

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