Wendi Li
Computer Scientist at University of Wisconsin-Madison
Madison, Wisconsin, United States
Summary
👤
Senior🎓
Top SchoolWendi Li is a computer scientist with nine years of experience and an MS in Computer Science from the University of Wisconsin–Madison, currently based in Madison, WI. She interned with Microsoft Research Asia where she contributed to the widely used Qlib quantitative investment platform, integrating and adapting the Temporal Fusion Transformer for financial time-series prediction. Her research work there produced a meta-learning based reweighting approach and a Meta-Controller/Reweighter framework to improve model generalization on unseen market data. Comfortable moving between research and engineering, she focuses on practical ML system integration, data feeding pipelines, and reproducible experimentation. Wendi’s background spans top-tier academic training (UC Berkeley coursework and a BE from South China University of Technology) and hands-on open-source impact in AI-driven quantitative finance.
9 years of coding experience
Non-degree, Electrical Engineering and Computer Sciences, Non-degree, Electrical Engineering and Computer Sciences at University of California, BerkeleyMaster of Science - MS, Computer Science, Master of Science - MS, Computer Science at University of Wisconsin-MadisonBachelor's degree, Computer Science, Bachelor's degree, Computer Science at South China University of Technology
Github Skills (10)
machine-learning10
deeplearning-ai10
deep-learning10
tensorflow10
python10
data-format9
algorithmic-trading9
quantitative-finance9
finance9
data-formats9
Programming languages (3)
Github contributions (5)
microsoft/qlib
Sep 2020 - Jan 2023
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
Role in this project:
ML Engineer
ML EngineerContributions:3 reviews, 43 commits, 29 PRs in 2 years 3 months
Contributions summary:Wendi primarily contributed to the TFT (Temporal Fusion Transformer) model within the Qlib framework, focusing on the integration and adaptation of this model for financial time-series prediction. Their work involved modifying existing code, updating configuration files, and adjusting parameters specific to the Alpha158 dataset. The user also made minor corrections and formatting changes to documentation and example code related to the TFT model, demonstrating a focus on practical application of the model within the project's objectives.
aimachine-learningsupervised-learningquantitative-financestock-data
wendili-cs/leetcode
Apr 2021 - Nov 2022
Contributions:366 commits, 452 pushes in 1 year 7 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.