Media Mix Modelling
summary
Bayesian Media Mix Modelling shows how attribution, adstock and spillover, and daily-level channel data pin down which buys actually move revenue. A deployed model flags Apple Store installs as the worst-performing source and leads to saved €1,000,000+ by cutting wasted spend. Implementation uses the PMC marketing ecosystem and experiments with Meridian for rapid prototyping; beware differences in units (impressions vs spend), heavy intercepts, and low-signal channels that require more budget to evaluate.
AI-written summary · about
chapters (13)
- 0:00Media Mix Modelling intro
- 3:03Why MMM matters now
- 6:00Bayesian approach in MMM
- 8:29Cookie policy case study
- 12:29Evaluating marketing channels
- 15:18Data scientists and marketers
- 17:27Common MMM mistakes
- 20:20Control channels and seasonality
- 22:32Data prep and model expectations
- 24:44Model results and stakeholder communication
- 25:28MMM tools and libraries
- 27:36Budget allocation tips
- 28:17Conclusion and MMM future
related talks
39mHow to Allocate Marketing Budget - Bayesian Approach to the Rescue
31mMedia Mix Modeling:How to Measure the Effectiveness of Advertising
30mIs your marketing effective? Let Bayes decide!
27mUsing Causal thinking to make Media Mix Modeling
29mDeciphering Sales Drivers at PepsiCo
27mEmpowering Business to make model-based marketing decisions
21mHow to Get Ahead in Advertising
30mMMM and MTA: The Future of AI-Driven Marketing