Hey! I'm Yueyue, a CS & Public Policy graduate student @UChicago
I'm deeply passionate about data science and analysis. Originally from China, I ventured to the United States to pursue my undergrad and master's degree. Prior to delving into graduate school, I garnered four years of professional experience in the data field (internships).
Check out my projects
About Me
My academic foundation was laid at Syracuse University, where I majored in Information Science and Supply Chain Management. Over a span of four years, I cultivated a strong proficiency in data cleaning, cleaning, management, analysis, and visualization. My academic pursuits were further enriched with hands-on experience during four internships, where I honed my capabilities as a data analyst.
Venturing further into the world of data science and software development, I found a profound passion and calling. I currently serve as a Data Analyst at the Office of Civic Engagement at UChicago. Here, I have not only mastered unstructured data cleaning and analysis but have also excelled in fostering cross-departmental communication and driving program development, scoping, assessment, and evaluations.
My Projects
Food Accessibility in Chicago
An interactive web app powered by Dash library in Python.
Github Link
OCE Stakeholder Map
A interactive web app powered by ArcGIS Online.
Demo
Global Shipping Analysis Dashboard Powered by Tableau
Data Analyst Apprenticeship Under Supervision of Lyu, Lead Data Engineer at Amazon - Designed and deployed a Tableau dashboard analyzing 2021 global shipping trends across multiple countries, pinpointing district shipping anomalies and assessing overall logistics efficiency. Designed and implemented an automated ETL pipeline with PostgreSQL and Python, streamlining data processing, leading to accelerated reporting times by 30%.
Affordable Housing and Public Transportation Access
An interactive web map powered by ArcGIS.
Demo
Sensor-driven Movement Classification
Data Scientist Apprenticeship Under Supervision of Yihan Wang, Software Engineer at Google - Cleaned and detected anomalies in a 1-million-row sensor-driven movement dataset using Scikit-learn, achieving a 95.5% accuracy in data consistency checks, laying the foundation for the motion classification. Employed Scikit-learn to apply K-Nearest Neighbors and Random Forest algorithms on accelerometer data, achieving a 92% accuracy in classifying participants' movement patterns