Skip to content
Marketing Intelligence
MBA Marketing Beyond Advertising

Media Mix Modelling (MMM)

Media Mix Modelling (MMM): A statistical analysis technique that measures the contribution of each marketing channel to overall business outcomes.

Media mix modelling (MMM), also called marketing mix modelling, uses statistics to estimate how much each channel contributes to sales or other outcomes. It analyses aggregated data over time (spend by channel, sales, prices, seasonality, promotions, competitor activity) rather than tracking individual users.

Why it is back in favour: because it needs no cookies or user-level tracking, MMM is robust to privacy changes that have weakened attribution. It also captures channels that are hard to track, such as TV, out-of-home and brand effects.

Open-source options: Google’s Meridian and Meta’s Robyn have made MMM far more accessible. Meridian, for example, can be calibrated with experiment results and models reach and frequency for video.

Limits: MMM needs a couple of years of reasonably varied data, works at a high level rather than by campaign, and can mistake correlation for causation. The best practice is to calibrate it with incrementality tests.

MBA Editorial ·

Sources

  1. Meridian, Google for Developers
  2. Robyn, Meta

Related terms