NYC Neighborhood Opportunity Index
Built a neighborhood ranking model using public NYC + Census data to help compare areas on affordability, safety, and transit access.
Python
SQL
Data Cleaning
Visualization
Problem
Choosing where to live, recruit, or launch a small business in NYC involves tradeoffs: rent vs. safety vs. commute time. I wanted a single, transparent scoring framework that compares neighborhoods consistently and makes the tradeoffs easy to see.
Data
- NYC Open Data (public safety / incidents; neighborhood boundaries where applicable)
- Transit access (subway station locations / proximity measures)
- Census / ACS-style indicators (income, rent/affordability proxies)
Approach
- Cleaning: standardized neighborhood names, handled missing values, removed duplicates.
- Feature engineering: created metrics for affordability, safety, and transit access.
- Scoring model: normalized metrics and combined them into an overall “Opportunity Score.”
- Outputs: produced a ranked table and visual summaries for quick comparison.
Results
- Created a repeatable scoring pipeline that can be updated as new public data is released.
- Generated a ranked view that highlights neighborhoods that are strong on transit + affordability tradeoffs.
- Packaged results in a format that can feed a dashboard (map + filters) as a next step.
What I’d do next
- Add interactive map filtering (by borough, budget range, commute threshold).
- Validate scoring weights with sensitivity testing (how rankings change when weights change).
- Add a “commute-to” feature: optimize for travel time to Midtown / FiDi / specific address.