Alex Hayes
Postdoctoral Scholar at Stanford University
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAlex Hayes is a statistician and postdoctoral researcher with a decade of experience building scalable analytical methods, causal inference tools, and user-friendly software for networked data. His PhD work at UW–Madison produced methods and nine CRAN packages that scale network and matrix computations by orders of magnitude, enabling analysis of networks with millions of nodes. He combines rigorous causal machine learning with pragmatic engineering—reducing computation by 5000x in some pipelines—and has shipped production-ready code used by the tidyverse (notably contributions to broom and recipes). Based in Palo Alto, he has advised product teams at Meta, prototyped cost-saving model evaluations, and continues to focus on making network experiments more cost effective.
10 years of coding experience
Doctor of Philosophy - PhD Statistics, Doctor of Philosophy - PhD Statistics at University of Wisconsin-MadisonBachelor of Arts - BA Statistics, Bachelor of Arts - BA Statistics at Rice University
English, Spanish
Stackoverflow
683reputation
59kreached
10answers
13questions
Github Skills (20)
r10
testing10
feature-engineering10
data-preprocessing10
statistical-models10
data-analysis10
decomposition9
matrix-decomposition9
machine-learning9
data-wrangling9
eigenvalue9
svd9
vector6
rlang6
optimization6
Programming languages (11)
Github contributions (5)
tidymodels/broom
Dec 2017 - Jun 2021
Convert statistical analysis objects from R into tidy format
Role in this project:
Back-end Developer
Back-end DeveloperContributions:5 releases, 11 reviews, 327 commits in 3 years 6 months
Contributions summary:Alex's contributions primarily revolve around enhancing the `broom` package's statistical analysis capabilities. Their commits focus on implementing and extending tidying methods for statistical analysis objects, like `svd`, to improve the package's usability and functionality. This includes adding new methods like `add svd augment` and extending them to irlba objects, as well as refactoring the existing codebase to integrate new functionality to tidy statistical analysis objects from R.
r-packagestatisticshypothesis-testingregression-modelstidymodels
tidymodels/recipes
Jul 2017 - Feb 2018
Pipeable steps for feature engineering and data preprocessing to prepare for modeling
Role in this project:Data Scientist
Data ScientistContributions:22 commits, 4 PRs, 30 comments in 7 months
Contributions summary:Alex implemented and refined recipe steps for feature engineering and data preprocessing within the tidymodels framework. Their contributions focused on the `step_intercept` and `step_relu` functions, adding functionality and correcting example code. The user also contributed to testing these new features. The work enhances the recipes package by providing key preprocessing transformations for machine learning workflows.
pythondata-preprocessingmachine-learningengineeringprepare
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.