Ali Kozlu

Data Scientist

San Francisco, California, United States
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Ali Kozlu is a data scientist with a decade of experience applying machine learning to real-world problems, currently shaping analytics at Swish Analytics in San Francisco. He earned a BASc in Computer and Cognitive Science from the University of Pennsylvania, with a minor in Data Science. Early in his career, he helped build an electronic document classifier for Turkish telecoms, delivering models that detect signatures, read handwriting, and classify customer forms—adopted by Turkcell and Vodafone. His work spans research-driven data science and production-grade software engineering, enabling end-to-end ML solutions from idea to deployment. Based in the Bay Area, he brings an international perspective from his studies in Istanbul and professional experience across Turkey and the United States.
code10 years of coding experience
bookGerman High School of Istanbul
bookBachelor of Applied Science (BASc), Computer & Cognitive Science, Bachelor of Applied Science (BASc), Computer & Cognitive Science at University of Pennsylvania
languagesTurkish, English, German
github-logo-circle

Github Skills (57)

packaging10
resolver10
data-quality9
eda9
python9
statistics9
pipeline9
data-analysis8
dataquality8
data-integrity8
datacleaning8
machine-learning8
data-profiling8
exploratory-data-analysis8
data-science8

Programming languages (4)

RustTeXJupyter NotebookPython

Github contributions (5)

github-logo-circle
akozlu/TennisPrediction

Jun 2018 - Apr 2019

This project proposes a novel approach for tennis modeling by introducing stacking, an ensemble learning technique used to combine information from multiple predictive models to generate a new model, a so called super learner. A historical dataset of 101295 ATP tennis matches played between 2004-2014 is used to train the meta-model.
Contributions:47 PRs, 65 pushes, 11 branches in 10 months
metaensembleensemble-learningatptennis
This repo includes minor changes to open source great_expectations library to make it compatible for Python 3.5.3.
Contributions:2 PRs, 14 pushes, 4 branches in 24 days
minorpythongreat-expectationsexpectationspython-3
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.
Request Free Trial