Vincent Blot
Ph.D Student - Data Scientist
Paris, Ile-de-France
Summary
🤩
Rockstar🎓
Top SchoolVincent Blot is a Paris-based Ph.D. student and data scientist with six years of experience applying AI, computer vision and uncertainty quantification to healthcare and industry problems. He has blended research and product work at Quantmetry and Capgemini Invent, developing CNN-based detection pipelines for biomedical imagery and advancing conformal prediction tooling in the scikit-learn-contrib MAPIE project. His background in econometrics and statistics informs a rigorous, measurement-driven approach to model evaluation and prediction-interval estimation. Vincent’s contributions emphasize code quality, cross-validation improvements and reproducible testing—skills he pairs with hands-on deep learning implementation in PyTorch and Keras. Notably, he bridges academic research (LISN doctoral work) and production-ready solutions, making uncertainty-aware models practical for real-world decision-making.
6 years of coding experience
6 years of employment as a software developer
Master 2 Econometrics and Statistics Statistic, Master 2 Econometrics and Statistics Statistic at Toulouse School of Economics
Github Skills (6)
scikit-learn10
python10
classification10
scikit10
testing9
regression4
Programming languages (1)
Github contributions (5)
scikit-learn-contrib/MAPIE
Dec 2021 - Jan 2023
A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.
Role in this project:
Data Scientist
Data ScientistContributions:5 releases, 729 reviews, 20 commits in 1 year 1 month
Contributions summary:Vincent primarily contributed to the testing and enhancement of the `mapie` library, specifically focusing on the `MapieClassifier` class. They modified test cases for classification, added functionality related to cross-validation, and removed unnecessary conditions in the code. The user also addressed linting errors and added references, reflecting a focus on code quality and documentation within the context of conformal prediction for classification.
regressionpythonconfidence-intervalspredictiondata-science
conda-forge/mapie-feedstock
Jan 2023 - Jan 2025
A conda-smithy repository for mapie.
Contributions:12 PRs, 12 pushes, 1 comment in 2 years
condasmithy
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.