Project Robyn 3.0: Continuous & Semi-Automated Marketing Mix Model from Facebook Marketing Science by Bernardo Lares & Igor Skokan Visit https://rstats.ai/nyr/ to learn more. Abstract: Robyn is an experimental, semi-automated and open-sourced Marketing Mix Modeling (MMM) package from Facebook Marketing Science. It uses various machine learning techniques (Ridge regression with cross validation, multi-objective evolutionary algorithm for hyperparameter optimisation, time-series decomposition for trend & season, 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 data sources. Bio: Bernardo Lares is a Venezuelan Marketing Science Partner at Facebook, currently located in Colombia, passionate about data science, automation, data visualization, and R. He has mainly engaged in FinTech, Insurance, and Marketing projects, applying data science to real-world problems, and helping clients and consumers get the most out of the data available. Bernardo has an open-source R package called `lares` mainly designed to democratize AutoML with a plug-and-play approach to train Machine Learning models, ready to deploy. It also holds dozens of other functionalities to help analysts with their daily tasks. He likes to describe his package as a "shared side-kick that boosts your analytics." Currently, he is developing internal and external Marketing Science solutions at Facebook with R; one of the most impactful projects is Robyn, which helps empower mid-sized businesses to semi-automate their marketing mix models using open-source solutions. Twitter: https://twitter.com/LaresDJ Bio: Igor [Iggy] is part of the global Marketing Science team at Facebook based in London, helping agencies and marketers find true business value through a range of solutions designed to measure audience, brand and sales outcomes. Nuclear scientist & mathematician by education, prior to joining Facebook, Igor held various senior analytical positions within Omnicom’s data, tech and analytics units in Dubai, London and Prague. Across his roles before and now, his focus is on intersection of different facets of marketing effectiveness from contemporary MMM, holistic attribution, RCTs/experimentation to media insights. Beyond his passion for numbers, he likes traveling, ultra-trail running and climbing (high) mountains. Presented at the 2021 New York R Conference (September 10, 2021)