Andrew Gelman
New York, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolAndrew Gelman is a quantitative trader and data scientist in New York with 11 years of experience applying systematic, reproducible approaches to forecast individual stocks and market direction. He blends fundamental analysis with Bayesian and statistical modeling—contributing Stan models for real-world problems like sports rating systems and specialty regression applications. Comfortable coding in Python and Java, he focuses on translating probabilistic models into actionable trading signals and risk-aware strategies. His work on the well-known stan-dev/example-models repository underscores a deep practical familiarity with hierarchical and mixture models. Andrew pairs market intuition with rigorous model specification, favoring interpretable, testable systems over black-box solutions. Colleagues describe him as methodical and pragmatic, often uncovering predictive edges through careful model design rather than brute-force complexity.
11 years of coding experience
Stony Brook University
Github Skills (5)
bayesian-statistics10
bayesian10
stan10
statistical-models10
r9
Programming languages (7)
Github contributions (5)
stan-dev/example-models
Jun 2018 - Oct 2019
Example models for Stan
Role in this project:
Data Scientist
Data ScientistContributions:14 commits, 12 pushes, 4 comments in 1 year 3 months
Contributions summary:Andrew primarily contributes by creating and modifying Stan models. They develop and refine statistical models for various datasets, including a regression model, a golf putting model with geometric analysis, and a mixture model. The user also works on models related to World Cup data and rating systems. Their work involves defining parameters, model specifications, and generating quantities, indicating a focus on Bayesian statistical modeling and inference.
stan
bob-carpenter/diagnostic-testing
May 2020 - Jul 2020
statistical models to analyze diagnostic tests
Contributions:19 commits, 15 pushes in 1 month
statistical-models
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.