Today we got our project assignments for summer 2015, and I was excited to be assigned to the Fire team! This is a project with the Atlanta Fire Rescue Department (AFRD) using all kinds of interesting datasets to predict fire risk of different buildings throughout Atlanta. This way, the AFRD can better allocated their building inspection resources. The DSSG Fire team includes myself (Oliver Haimson), Wenwen Zhang, Michael Madaio, and temporarily Xiang (Sean) Cheng. Our faculty advisors are Polo Chau and Bistra Dilkina.
I was drawn to this project because of its potential for real world impact in reducing fire risk, which can save lives if successful. I’m excited to build statistical and machine learning models to predict fire risk, not only using the data provided to us by AFRD, but also using social media data. I think that we may be able to predict fire risk by looking at the ways that people talk about particular businesses on sites like Yelp and Twitter.
After we got our data this morning, we got to work on familiarizing ourselves with the different datasets. Wenwen, who is a GIS and spatial modeling wizard, wasted no time in creating some initial geospatial visualizations. Here’s an example of a heat map of fires in Atlanta.
I spent the day looking through the variables included in the different datasets, and thinking about which ones may be useful as predictor variables in a fire risk model. I think that one of the hardest parts of this project will be matching up the buildings in the different datasets. Many buildings are in one dataset but not others, the address formats are different in the different datasets, and the fire data is often recorded as intersections or at imprecise addresses. We remain hopeful that we may be able to identify the buildings using geo-coordinates and parcel data.
We then met with Matt Hinds-Aldrich, AFRD’s Senior Management Analyst. Matt was extremely generous with his time and spent several hours going through the datasets with us and helping us to understand the data better. He also articulated AFRD’s goals to be able to better predict fire risk in order to inspect the most at-risk buildings. As he describes it, this is a process to discover the “unknown unknowns” – buildings that AFRD doesn’t know that they don’t know they need to inspect. We set up weekly meetings for the rest of the summer (including a visit to their headquarters next week!), and talked about potential opportunities for our team to tag along with fire inspectors to better understand the everyday details of fire inspection.
Our team is very excited to keep working on this fascinating problem, and we hope that our work this summer will eventually make an impact on fire prevention in Atlanta!