Kay Brodersen
Senior Staff Data Scientist
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolKay Brodersen is a Senior Staff Data Scientist at Google in Zurich with 11 years of experience leading teams that solve core measurement, experimentation, and causal-inference problems for Ads. He holds a PhD in Statistics and Machine Learning from ETH Zurich and a strong academic background across Münster, Cambridge and Oxford, with 25+ peer-reviewed publications. Kay built and scaled statistical tooling used across Google—authoring the widely used open-source CausalImpact R package (20k+ monthly downloads) and creating a top Bayesian time-series anomaly detector adopted by dozens of product teams. He combines deep probabilistic modelling expertise with product-facing experimentation design and long-term strategy, mentoring teams across the US and Switzerland. An underappreciated strength is his track record of moving research-grade Bayesian methods into terabyte-scale production systems that influence business decisions.
11 years of coding experience
7 years of employment as a software developer
MSc, Information Systems, MSc, Information Systems at University of MünsterVisiting undergraduate, Computer Science, Visiting undergraduate, Computer Science at University of CambridgeMSc, Neuroscience, MSc, Neuroscience at University of OxfordPhD, Statistics and Machine Learning, PhD, Statistics and Machine Learning at ETH Zurich
Stackoverflow
227reputation
6kreached
3answers
0questions
Github Skills (10)
bayesian-statistics10
bayesian10
causal-inference10
r10
data-analysis9
statistical-models9
time-series9
causality6
ggplot6
java6
Programming languages (1)
Github contributions (5)
google/CausalImpact
Aug 2014 - Oct 2022
An R package for causal inference in time series
Role in this project:
Data Scientist
Data ScientistContributions:61 commits, 4 PRs, 14 pushes in 8 years 3 months
Contributions summary:Kay primarily contributed to the project by modifying existing code related to causal inference analysis and documentation. They focused on renaming variables and result columns to align with plot function expectations. The user also fixed issues related to missing data in the pre-period response variable, ensuring the correct output for a causal impact analysis. Finally, the user corrected a typo in the automatic report generation.
r-packagetime-series-analysiscausalinferencetime-series
kaybrodersen/kaybrodersen.github.io
Jan 2017 - May 2023
Contributions:24 pushes, 1 branch in 6 years 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.