Keith Battocchi
Software Engineer at Microsoft
Newton, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolKeith Battocchi is a software engineer with 13 years of experience at Microsoft and a strong academic foundation from MIT in math, electrical engineering, and computer science. He combines production-grade software engineering with applied machine learning, contributing to Microsoft Research projects and the py-why/econml toolkit to advance causal inference methods in economics. His work on Double Machine Learning, discrete treatment support, pandas compatibility, and model serialization has helped make state-of-the-art causal tools more usable in real-world workflows. Based in Newton, MA, he brings deep domain knowledge from both research and engineering roles, having started his career at Tessella and supported MSR as an F# contractor. Colleagues describe him as a pragmatic problem-solver who bridges rigorous theory and production pragmatics. He often surfaces non-obvious efficiencies in tooling that lower the barrier for analysts to apply causal methods at scale.
13 years of coding experience
6 years of employment as a software developer
B.S., MEng, Math, Electrical Engineering and Computer Science, B.S., MEng, Math, Electrical Engineering and Computer Science at Massachusetts Institute of Technology
Stackoverflow
55,034reputation
1.8mreached
868answers
0questions
type-conversion
top-5%
extension-methods
top-5%
linq
top-5%
interop
top-1%
recursion
top-5%
clr
top-5%
Github Skills (46)
python10
scikit10
pandas10
machine-learning10
inline10
econometrics10
interop10
causal-inference10
statistical-models10
scikit-learn10
generics10
linq9
constructor9
clr9
linq-to-sql9
Programming languages (7)
Github contributions (5)
py-why/EconML
Feb 2019 - Jan 2023
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:30 releases, 470 reviews, 265 commits in 3 years 11 months
Contributions summary:Keith primarily focused on enhancing the EconML library for causal inference, particularly within the context of the py-why/econml repository, which utilizes machine learning for economic decision making. Their contributions include implementing and refining Double Machine Learning (DML) models, including enhancements for discrete treatment analysis, feature engineering, and model serialization. The user improved the usability and functionality of several key components of the library, making them compatible with pandas and facilitating broader application in real-world settings.
decision-makingfairness-mlpythonoutcomeproblems
kbattocchi/EconML
Mar 2023 - Mar 2025
Contributions:157 pushes, 19 branches in 2 years
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.