Saulo Mastelini
Data Scientist
São Paulo, Brazil
Summary
🤩
Rockstar🎓
Top SchoolSaulo Mastelini is a data scientist and PhD in Online Machine Learning from USP with 11 years of experience building production-ready ML solutions and research-grade algorithms. He has driven time-series forecasting and broader ML tooling at Volt Robotics and now works at Kunumi, blending applied consulting with research instincts. A core developer and maintainer of River, he has contributed significant multi-target regression metrics and split-criteria to a widely used online-ML Python library, reflecting deep expertise in streaming/online learning, regression, decision trees and nearest-neighbor search. His academic background and visiting research roles inform a rigorous approach to evaluation frameworks and model metrics that often distinguishes practical systems from theoretical prototypes.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Online machine learning, Doctor of Philosophy - PhD, Online machine learning at Instituto de Ciências Matemáticas e de Computação (ICMC) - USPMaster of Science - MS, Machine Learning - Multi-target regression, Master of Science - MS, Machine Learning - Multi-target regression at UEL - Universidade Estadual de Londrina
Portuguese, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
regression10
machine-learning10
develop10
python10
meter10
metric10
data-science9
data-analysis9
elearning9
incremental-learning9
algorithm9
algorithms9
Programming languages (5)
Github contributions (5)
online-ml/river
Aug 2018 - Jan 2023
🌊 Online machine learning in Python
Role in this project:
ML Engineer
ML EngineerContributions:497 reviews, 349 commits, 128 PRs in 4 years 5 months
Contributions summary:Saulo's commits primarily focused on adding and modifying metrics related to Basic MTR (Multitarget Regression) in the `online-ml/river` repository. The code changes introduced basic metrics like MAE and AMSE. Further, the user added new multi-target regression metrics (AMAE and ARMSE) and relevant calculations within the evaluation framework.
stream-processingpythonstreaming-datadata-scienceonline-statistics
scikit-multiflow/scikit-multiflow
Aug 2018 - Aug 2020
A machine learning package for streaming data in Python. The other ancestor of River.
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:168 commits, 40 PRs, 33 pushes in 1 year 11 months
Contributions summary:Saulo added essential metrics to the evaluation framework, specifically for Multi-target Regression (MTR) tasks, indicating a focus on the project's machine learning capabilities. They extended the functionality of the evaluation and measurement classes to handle MTR problems by incorporating AMSE, AMAE, and ARMSE metrics. Furthermore, the user integrated a new IntraClusterVarianceReductionSplitCriterion to enable better splitting for MTR tasks. The changes suggest contributions in the core evaluation and algorithm components.
moapythonstreaming-datariverancestor
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.