Mogeng Yin
Applied Machine Learning Research Scientist at Facebook
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolMogeng Yin is an applied machine learning research scientist with 11 years of experience, combining a PhD in Transportation Engineering and an MS in Computer Science from UC Berkeley with a strong academic record. He applies spatial-temporal data mining and deep learning to real-world problems—publishing on mobile-phone-based activity recognition, travel demand forecasting, and developing the pip-installable IOHMM package. At Facebook he focuses on improving ads ranking predictability and advertiser value, translating research-grade models into production impact. His background in transportation simulation and large cellular-data analysis gives him a unique edge in marrying mobility domain knowledge with modern sequence and reinforcement learning methods.
11 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy (PhD), Civil Engineering, Transportation, 3.92/4.0, Doctor of Philosophy (PhD), Civil Engineering, Transportation, 3.92/4.0 at University of California, BerkeleyBachelor of Engineering (B.Eng.), Civil Engineering, 91/100, Bachelor of Engineering (B.Eng.), Civil Engineering, 91/100 at Tsinghua UniversityExchange program, Civil Engineering, 4.75/5, Exchange program, Civil Engineering, 4.75/5 at National University of Singapore
Github Skills (19)
python10
sequence-labeling10
machine-learning10
graphical-models10
time-series10
semi-supervised-learning10
linear-models10
unsupervised-learning10
statsmodels10
supervised-learning10
scikit-learn10
sequence-to-sequence10
hidden-markov-model10
backend8
reinforcement-learning5
Programming languages (3)
Github contributions (5)
Mogeng/IOHMM
Feb 2016 - Feb 2021
Input Output Hidden Markov Model (IOHMM) in Python
Contributions:1 release, 3 reviews, 60 commits in 5 years
hidden-markov-modelpythongraphical-modelssequence-to-sequencemachine-learning
Mogeng/githubtest
May 2015 - May 2015
Contributions:3 pushes in 1 day
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.