Peter Foley is Head of Data Science with a decade of experience building and leading teams that turn causal inference and machine learning into production products for media and advertising. He currently architects the modeling core for EDO’s AdEngage, predicting household-level responses to TV and streaming ad exposures while maintaining clean, maintainable code and deployment pipelines. A former founder and analytics lead in political and media spaces, he combines deep expertise in experiment design, heterogeneous treatment effect analysis, and behavioral modeling with hands-on ML engineering. Peter is an active contributor to open-source causal ML (notably refactoring and validating components in uber/causalml) and brings a rare blend of academic rigour from Caltech and practical product-driven delivery.
Uplift modeling and causal inference with machine learning algorithms
Role in this project:
ML Engineer
Contributions:7 commits, 5 PRs, 19 comments in 28 days
Contributions summary:Peter contributed significantly to the `causalml` repository, focusing on improvements and refactoring of existing causal inference and uplift modeling tools. Their commits include fixing typos, generalizing existing functions, and adding treatment validation across various learner classes. They also refactored and validated the `CausalTreeRegressor` and made updates related to the XGBoost library.
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.