Summary
Jiayuan G is a Data & Applied Scientist at Microsoft with nine years of experience applying statistical analysis, machine learning, and visualization to genomics and fraud-detection problems. Trained in chemical engineering with an advanced data science focus from the University of Washington, she builds end-to-end solutions—SQL-backed data pipelines, scikit-learn models (PCA, k-means, random forest, SVM), and interactive dashboards using Tableau and Plotly/Dash. Her graduate research produced a visualization tool for unsupervised analysis of RNA‑seq data, blending domain knowledge in bioinformatics with pragmatic production skills on AWS and Git. Equally comfortable in exploratory data analysis and feature selection, she maintains a public data-science portfolio demonstrating reproducible projects spanning NGS genomics and applied fraud detection.
9 years of coding experience
3 years of employment as a software developer
Training Program, Data Science: Data-Intensive Research Enabling Clean Technologies (DIRECT), Training Program, Data Science: Data-Intensive Research Enabling Clean Technologies (DIRECT) at University of Washington
Bachelor of Science - BS, Chemical Engineering, Bachelor of Science - BS, Chemical Engineering at Tianjin University
Chinese, English