Frankie Cancino
Senior Data Scientist
San Francisco, California, United States
Summary
👤
Senior🎓
Top SchoolFrankie Cancino is a Senior Data Scientist based in San Francisco with a decade of experience building production-ready ML systems and data platforms, currently driving Data & AI work at Mercedes‑Benz R&D. He blends applied machine learning, time series expertise, and production engineering—having built a streamlined ML platform, optimized Keras models for multi-node NVIDIA training, and deployed deep learning frameworks across 1,000+ nodes. At Target he improved demand-forecasting explainability and performance through item-similarity and community-detection techniques, and combined matrix profile methods with deep learning for intelligent anomaly detection. An active contributor to open-source tooling, he helped stabilize the widely used matrixprofile-ts project by strengthening its test infrastructure and sampling strategies. Frankie also founded an internal Data Science Education cohort and champions responsible AI practices across enterprises. His background in IT and an MS in Business Analytics give him a rare mix of engineering rigor and business-facing model stewardship.
10 years of coding experience
5 years of employment as a software developer
University of Minnesota Twin CitiesUniversity of Missouri
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (4)
pytest10
python10
testing10
numpy8
Programming languages (6)
Github contributions (5)
target/matrixprofile-ts
Sep 2018 - Apr 2020
A Python library for detecting patterns and anomalies in massive datasets using the Matrix Profile
Role in this project:
QA Engineer / Test Automation Engineer
QA Engineer / Test Automation EngineerContributions:18 commits, 10 PRs, 7 pushes in 1 year 7 months
Contributions summary:Frankie primarily focused on improving the project's testing infrastructure. They fixed import paths within the test suite, ensuring the tests could correctly locate the necessary modules. Furthermore, the user added a sampling parameter to three tests, potentially to allow testing of a wider variety of scenarios. Their commits demonstrate a clear focus on ensuring the reliability and correctness of the `matrixprofile-ts` library.
pythonpypipipmotifpypi-packages
frankiecancino/PersonalSite
Apr 2018 - Sep 2024
Contributions:11 PRs, 59 pushes, 4 branches in 6 years 6 months
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.