/Robyn

Robyn is an experimental, automated and open-sourced Marketing Mix Modeling (MMM) code from Facebook Marketing Science. It uses various machine learning techniques (Ridge regression with cross validation, multi-objective evolutionary algorithm for hyperparameter optimisation, gradient-based optimisation for budget allocation etc.) to define media channel efficiency and effectivity, explore adstock rates and saturation curves. It's built for granular datasets with many independent variables and therefore especially suitable for digital and direct response advertisers with rich dataset.

Primary LanguageRMIT LicenseMIT

No issues in this repository yet.