Isaac Lavine
Quantitative Researcher
Durham, North Carolina, United States
Summary
👤
Senior🎓
Top SchoolIsaac Lavine is a quantitative researcher at Susquehanna International Group who builds automated algorithms for options trading, combining a PhD in Statistics from Duke with nine years of applied modeling experience. His doctoral work partnered with 84.51 and Kroger to forecast daily sales across thousands of grocery items, and spawned PyBATS, an open-source Python package for Bayesian time series models. Earlier roles include a LinkedIn ML internship where he implemented Spark/Scala predictive models and a multi-objective feed-ranking optimizer, and Duke research applying deep learning to EHR data for mortality prediction. Isaac blends rigorous Bayesian methodology with production-ready engineering, focusing on scalable inference for count-valued time series and cross-series information sharing. Based in Durham, NC, he brings a rare mix of academic depth, open-source impact, and hands-on experience turning probabilistic models into deployable systems.
10 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Statistics, Doctor of Philosophy - PhD, Statistics at Duke University Graduate SchoolLafayette College
Stackoverflow
11reputation
385reached
1answer
0questions
Github Skills (5)
bayesian10
time-series-forecasting10
poisson6
time-series6
python6
Programming languages (1)
Github contributions (5)
lavinei/pybats_nbdev
Jul 2020 - Oct 2020
Bayesian time series forecasting and decision analysis
Contributions:76 commits, 72 pushes, 1 branch in 3 months
bayesiantime-series-forecasting
lavinei/pybats
Feb 2019 - Oct 2021
Bayesian time series forecasting and decision analysis
Contributions:124 commits, 5 PRs, 66 pushes in 2 years 8 months
bayesiantime-series-forecasting
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.