Marketing Science

Your MMM Should Not Predict Revenue

Revenue is a derived quantity. Marketing influences demand, units sold, not price. Modeling revenue directly entangles two mechanisms and produces misleading attribution.

12 janvier 2026
Partager
6 min de lecture

Which channels drive demand? Where should the next dollar go? What happens if we cut spend on display and shift it to TV?

To answer any of these, the model must isolate how marketing influences sales. And this is where most implementations make a structural mistake.

$$ \text{Revenue}t = f(\text{Marketing}t, \text{Seasonality}t, \text{Controls}t) $$

This seems natural. Revenue is the KPI the business tracks. It's what gets reported to the board.

À propos de l'auteur

Cyril Noirot

Cyril Noirot

Lead Data Scientist

Data scientist freelance. Je conçois et déploie des systèmes de décision — prévision, pricing, marketing measurement, optimisation.

Newsletter

Articles techniques sur la prévision, le pricing et les systèmes de décision. Aucune fréquence imposée.

Enter your email
Subscribe