Chandan Singh
Research Scientist at Senior researcher
Microsoft research, India
Summary
🤩
RockstarChandan Singh is a research scientist at Microsoft Research with 11 years of experience applying interpretable machine learning to science and medicine, informed by a PhD from UC Berkeley. He blends rigorous research with hands-on engineering—contributing production-ready code such as spelling-correction transformations for NL-Augmenter and interpretable model work in the imodels package. His contributions to BIG-bench show an aptitude for designing rigorous evaluation tasks and generating diverse, reproducible benchmarks for language models. Colleagues rely on him to translate complex ML concepts into usable code and tests, and he favors pragmatic organization (e.g., moving resources into JSON for reuse). Based in India, he combines academic depth with open-source impact across influential community projects.
11 years of coding experience
Github Skills (14)
scikit10
workbench10
json10
machine-learning10
nlp10
testbench10
spellchecking10
python10
spelling10
data-science10
spell10
scikit-learn10
text-generation9
decision-tree8
Programming languages (9)
Github contributions (5)
csinva/imodels
Jul 2019 - Jan 2023
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Role in this project:
Data Scientist
Data ScientistContributions:36 releases, 26 reviews, 417 commits in 3 years 7 months
Contributions summary:Chandan primarily contributed to the development of interpretable machine learning models, as indicated by the code comments and changes in the committed files. The user focused on adding code comments and modifications to example notebooks, including implementations related to model-based approaches such as DecisionTreeRegressor and RuleFit. These changes suggest the user was involved in either debugging or understanding, or adding to existing machine learning models in the imodels framework.
pythonxaisklearnsklearn-compatibleinterpretable
GEM-benchmark/NL-Augmenter
Aug 2021 - Sep 2021
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Role in this project:ML Engineer
ML EngineerContributions:12 reviews, 12 commits, 1 PR in 1 month
Contributions summary:Chandan primarily contributed to the implementation of a spelling correction transformation within the NL-Augmenter repository. They began by adding a basic transformation, expanding it with test cases, and subsequently refactoring the code. Their work involved defining a dictionary of common misspellings and integrating it into the sentence transformation process, which focused on text classification and generation tasks. Finally, the user moved the dictionary to a JSON file for better organization.
nlpinformation-theorysentencedeep-learningmachine-learning
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.