Yingtong Dou
Staff Research Scientist, Foundational AI
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolYingtong Dou is a Staff Research Scientist at Visa Research specializing in foundation models for payment services, with a decade of experience spanning graph mining, anomaly detection, and ML trust and safety. She builds and productionizes Transformer- and LLM-based models on multimodal transactional, tabular, and sequential data to improve authentication and authorization workflows. Her academic background (PhD, UIC) is grounded in impactful open-source work—she contributed key outlier-generation and evaluation modules to the widely used PyGOD graph outlier detection library. Prior roles include cross-industry collaborations with Tencent, Grab, F5, and Microsoft, and research internships exploring concept drift and fraud detection at Snap and Noah’s Ark Lab. Yingtong combines deep theoretical expertise with practical engineering to discover new foundation-model use cases in payments and to scale them into production.
10 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Internet of Things Engineering, 3, Bachelor's degree, Internet of Things Engineering, 3 at Beijing University of Posts and TelecommunicationsDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Illinois at ChicagoBachelor's degree, EECS, 3, Bachelor's degree, EECS, 3 at Queen Mary University of London
Spanish, Chinese, English
Github Skills (10)
graphdb10
pytorch10
machine-learning10
graph-neural-network10
anomaly-detection10
graphml10
python10
outlier-detection10
metric9
evaluation9
Programming languages (3)
Github contributions (5)
pygod-team/pygod
Nov 2021 - Jan 2023
A Python Library for Graph Outlier Detection (Anomaly Detection)
Role in this project:
Data Scientist / ML Engineer
Data Scientist / ML EngineerContributions:5 reviews, 52 commits, 2 PRs in 1 year 1 month
Contributions summary:Yingtong primarily contributed to the development of outlier detection functionalities within the PyGOD library. Their work involved creating modules to generate different types of outliers (structural and attribute-based) for benchmarking purposes, specifically focusing on attributed networks. These contributions were implemented using Python and PyTorch, demonstrating a focus on graph anomaly detection and machine learning techniques. The user also added evaluation metrics and example code to assess model performance.
graph-anomaly-detectionpytorchanomalypythonsecurity-tools
YingtongDou/ytongdou.github.io
Jan 2019 - Nov 2024
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Contributions:370 pushes in 5 years 11 months
templategithub-pages-templatemmistakesmistakesjekyll
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.