What is Robyn?
Robyn is an experimental, AI/ML-powered and open sourced Marketing Mix Modeling (MMM) package from Meta Marketing Science. The automation is enabled through various techniques like the multi-objective evolutionary algorithm for hyperparameter optimisation, time-series decomposition for trend & season, Ridge regression for model fitting & gradient-based optimizer for budget allocation. Robyn is built for granular datasets with many independent variables and therefore especially suitable for digital and direct response advertisers with rich data sources.
Why did we build this?
- Democratise modeling knowledge: We believe that transparency in measurement will build trust ultimately. We want to empower business of all sizes by transforming marketing practices grounded in data and science.
- Inspire the industry through innovation: We believe in advancing the industry by pushing boundaries of marketing science and collaborating with the like-minded.
- Reduce human bias: We believe in promising future of responsible & privacy-friendly AI/ML implementation to boost the efficiency of modeling, reduce human bias in the process and ultimately enable better decision making.
- Build a strong open source marketing science community: We believe in the power of open source that will further drive innovation in the industry and build strong bonds between practitioners.