NYC Traffic Safety & Crash Analysis | Northeast Big Data Innovation Hub & National Student Data Corps, in collaboration with
the U.S. Department of Transportation Federal Highway Administration
Analyzed 1.5M+ NYC crash records using Python to identify 10+ high-risk zones and temporal trends
across 5 boroughs,
applying Poisson and negative binomial regression on 100K+ crash events to quantify the impact of road
geometry on
accident rates
Built an interactive dashboard integrating 10+ risk factors, enabling real-time visualization of crash
data
Green Consumption Analytics in Vietnam | Finalist - Global Link Research Competition (2021)
Analyzed 200+ survey responses on green consumption using Python for trend identification
Applied NLTK for sentiment analysis on interviews with a local green store manager to assess market
challenges
Created interactive Tableau dashboards to visualize consumer insights and present findings to judges