Cheyanne Chow
UC Berkeley '26 | Data Science
Hi! I'm Cheyanne|
I'm part of UC Berkeley's graduating class of 2026 with a B.A. in Data Science and minor in City & Regional Planning. My past experience spans business analytics, GIS analysis, and predictive modeling, and I've worked with numerous organizations in the past to deliver data-driven insights.
If you have any questions or are looking to connect, feel free to reach out on any of my socials!
Education
University of California, Berkeley
B.A. in Data Science, Minor in City & Regional Planning
Aug 2022 - May 2026
Relevant Coursework
Experience
Business & Data Analytics Intern
Chinese Culture Center
- Analyzed 5,000+ Square transactions via EDA and regression, surfacing 3 distinct customer behavior patterns to inform targeted marketing strategies
- Discovered 3 cost-saving opportunities through comprehensive analysis of staffing patterns and rent expense optimization
- Built an automated reporting dashboard reducing insights generation time by over 80%
GIS Intern
SF Propel
- Built 3 spatial analyses and maps using ArcGIS illustrating potential impact areas for proposed family zoning policies across San Francisco neighborhoods
- Integrated 5+ datasets (census, parcel, housing inventory) for comprehensive spatial analysis of policy impacts and demographic trends
- Analyzed and cleaned 121,000+ site inventory sites across SF districts, addressing data quality issues to ensure accurate citywide policy coverage
Tinkering Specialist
Exploratorium
- Researched, developed, and prototyped 8-16 hands-on STEM-based projects annually (2-4 per season)
- Achieved 90%+ participant completion rates across all projects through effective instruction and engaging curriculum design
- Scheduled and coordinated semester-long curricula for 160+ San Francisco youth annually across 4 cohorts
- Maintained 95% on-time project delivery rate and zero scheduling conflicts through systematic planning and resource management
Projects
Air Delay Forecaster
Flight Delay Prediction Model
Developed XGBoost classification model to predict airline delays across 540,000 flights, achieving 67% accuracy and 0.64 recall through advanced feature engineering and analysis.
- Built 5+ features including weather susceptibility indicators for high-risk airports and distance-based flight categories
- Conducted comprehensive EDA using Pandas and Seaborn across 16+ airlines to identify delay patterns
- Identified airline carrier as the top delay predictor through feature importance analysis
Traffic Collision Injury Analysis
Crash Injury Predictor
Conducted regression analysis on 500K+ car collisions examining the impact of time and weather on injury severity using multivariate linear regression with interaction terms.
- Performed data cleaning and feature engineering on 15+ variables (weather, driver demographics, traffic)
- Built multivariate linear regression model identifying statistically significant predictors
- Discovered alcohol use increases injuries during afternoon (15%) and that weekends reduce injuries (12%)