I Built a Full-Stack NYC Neighborhood Intelligence App

📰 Medium · Python

Learn how to build a full-stack NYC neighborhood intelligence app using Python, Databricks SQL, XGBoost, and Streamlit to analyze 311 complaints and predict neighborhood trends

intermediate Published 17 Apr 2026

Action Steps

Pull 311 complaint data from NYC Open Data
Preprocess data using Databricks SQL
Train an XGBoost model to predict complaint patterns
Deploy the model using Streamlit for interactive visualization
Use SHAP explainability to interpret model results

Who Needs to Know This

Data scientists, software engineers, and urban planners can benefit from this tutorial to build a data-driven neighborhood intelligence system

Key Insight

💡 Combining data ingestion, machine learning, and visualization can provide valuable insights into neighborhood trends and patterns