Predicting Fire Risk and Prioritizing Fire Inspections

An Open Source Framework developed by Data Science for Social Good, Atlanta

Best Student Paper Award Winner (runner-up) at the ACM Knowledge Discovery and Data Mining 2016 conference!
Highlighted by the National Fire Protection Association as a best practice in using data analytics to improve fire safety.

What It Is

Firebird is a framework designed to help municipal fire departments:

  • Discover new properties for inspection
  • Prioritize those properties by their fire risk
  • Visualize property inspections on an interactive map
  • Improve all aspects of the inspection planning process
  • Developed through the Data Science for Social Good partnership between Georgia Tech and the Atlanta Fire Rescue Department.

    How It Works

      Step 1: Gather data sets with relevant commercial property information.
      Step 2: Join those data sets by each property's location data to create the most complete set of property records.
      Step 5: Assign a risk score to properties, and visualize them on an interactive map.


      Identifying and Prioritizing Fire Inspections: A Case Study of Predicting Fire Risk in Atlanta.
      Madaio, M., Haimson, O., Zhang, W., Cheng, X., Hinds-Aldrich, M., Dilkina, B., Chau, D.H.
      In Bloomberg Data for Good Exchange, 2015.


      National Fire Protection Association. Embracing Analytics: How communities around the country are utilizing data analytics to predict a host of risk factors and reduce fires.
      Georgia Tech College of Computing. When Computing Equals Social Good. Operating under the motto “engineers who speak human,” 14 undergraduate and graduate students – seven from the College – showed local organizations how advanced computational power and new analytic methods can help them make better decisions.

    Our Team

    Shang-Tse Chen

    PhD student in Computer Science at Georgia Tech

    Xiang Cheng

    PhD student in Computational Physics at Emory University

    Oliver Haimson

    PhD student in Informatics at University of California, Irvine

    Michael Madaio

    PhD student in Human-Computer Interaction at Carnegie Mellon University

    Wenwen Zhang

    PhD student in City and Regional Planning at Georgia Tech

    Dr. Duen Horng (Polo) Chau

    Professor of Computer Science at Georgia Tech

    Dr. Bistra Dilkina

    Professor of Computer Science at Georgia Tech

    Dr. Matt Hinds-Aldrich

    Senior Management Analyst at Atlanta Fire Rescue Department