Your MMM is Broken: Identification of Nonlinear and Time-varying Effects in Marketing Mix Models – MSI

Working Paper

Your MMM is Broken: Identification of Nonlinear and Time-varying Effects in Marketing Mix Models

Ryan Dew, Nicolas Padilla, Anya Shchetkina

Sep 30, 2024

Download

Analyzes advertising and sales data to demonstrate how two types of complex effects—nonlinearities and time-dependence—can be reliably inferred from standard marketing mix data, allowing marketers to choose the best model for optimization.

Topics

research recap

Avoiding Mix-Ups in MMMs: Experiments Can Distinguish Models for Optimization

Data privacy regulations that restrict individual-level tracking and targeting have renewed interest in aggregate marketing mix models (MMMs) to evaluate marketing effectiveness. Current methods conflate linear and time-varying models that have very different implications for resource allocation. Experiments can help marketers distinguish between and choose the appropriate model for optimization.

By using MSI.org you agree to our use of cookies as identifiers and for other features of the site as described in our Privacy Policy.