🔧 Keywords

Clustering, Geospatial Data, Web Scraping, K-Means, Demographic Analysis, NYC Open Data, Business Strategy

🧩 Problem

What’s the best neighborhood in NYC to open a new Zumba center — based on market demand and competition?

This project aimed to support business decisions by analyzing the geographic distribution of fitness centers, along with demographic and economic indicators tied to the Zumba target audience.

⚙️ What I Did

• Scraped NYC Open Data on:
  • Existing fitness centers
  • Socio-economic indicators by neighborhood
  • Demographic composition (incl. Hispanic population share)
• Performed exploratory analysis to identify underserved areas with business potential.
• Engineered features like fitness density, median income, rent levels, and unemployment rate.
• Applied K-Means Clustering to group neighborhoods into opportunity segments.
• Mapped and visualized the results using Folium to provide intuitive, location-based insights.

📊 Outcome

• Delivered a list of top recommended zones in NYC where Zumba centers could thrive, based on low competition and favorable demographics.
• Helped simulate a data-informed expansion strategy for boutique fitness brands or entrepreneurs targeting Hispanic-majority areas.
• Demonstrated how data science can be applied to urban business planning.

🛠️ Tech Stack