Improving Pittsburgh’s Educational Innovation Landscape, with Remake Learning
SUDS members: Carolina Arroyo (team lead), Allyson Fierro, Zach Goldstein, Sheena Jain, Eric Shapiro, Amit Sharma, Stephanie Truong, Angela Wang
Remake Learning is a professional network of educators and innovators working together to shape the future of teaching and learning in the Greater Pittsburgh Region, representing more than 250 organizations, including early learning centers & schools, museums & libraries, afterschool programs & community nonprofits, colleges & universities, ed-tech startups & major employers, philanthropies & civic leaders.
For this project, they want to better understand how their programs best support the areas of highest need in the city. To do this, the SUDS team is developing a set of interactive maps of the organizations that make up the Pittsburgh education innovation network, mapping the events they put on, and the populations they serve through those grant offerings and educational events. Our team is designing and developing interactive maps to visualize their data, both for their public-facing website and for their internal planning purposes. This also involves finding publicly available civic data on the City of Pittsburgh area, such as, for instance, census data, and integrating it into either the maps and a data dashboard for Remake Learning planning purposes.
Understanding Fresh Food Access in Pittsburgh, with Just Harvest
SUDS members: David Mitre Becerril (team lead), Jessica Young, Sukrit Ajmani, Ashish Arora, Angela Liu, Julie Kim, Bai Xue, Jennifer Yang
Just Harvest is a non-profit organization working to end hunger by expanding access to fresh, healthy food. The Fresh Access program helps enable shoppers to use their food stamps – as well as credit and debit cards – to buy fresh, nutritious, and locally-grown food.
For this project, they want to better understand the population they serve and the farmers’ markets currently supported through Fresh Access. To do this, they want to develop an interactive map to visualize and understand the transactions that occur at the ~300 markets they work with, to better target their support and plan for future market partnership. Our team of SUDS students is designing and developing this interactive visualization of their transaction and market data and developing a pipeline so the map can be updated as new data are collected. This also involves finding and integrating publicly available civic data on the City of Pittsburgh area, such as, for instance, census data or SNAP data. As part of this work, they are also conducting additional statistical analyses to understand the pattern of market usage from their Fresh Access users.
Fire Risk Predictive Analytics, with Metro21, Pittsburgh Bureau of Fire, and Pittsburgh Department of Innovation and Performance
SUDS members: Palak Narang (team lead), Jeffrey Chen, Fangyan Chen, Nathan Kuo, Jessica Lee, Amaya Taylor, Xingyuan Ying
Metro21 is a partnership between CMU and the City of Pittsburgh and Allegheny County, to support research, development, and deployment of CMU projects that seek to solve problems in a variety of metro-related focus areas. This project is in partnership with the Pittsburgh Bureau of Fire (PBF) and the Department of Innovation and Performance.
For this project, PBF wants to understand the relative fire risk of various properties around the city, to inform their Community Risk Reduction efforts (e.g. property inspections and fire safety education events). To do this, Metro21 has already developed a machine-learning risk model trained on historical fire incident data and various features of commercial properties in the city. PBF is currently using this risk model to inform their fire inspections, but they want to improve and extend the model further with new data sources, including developing a risk model for residential properties in addition to the commercial properties already included in the model.
Our team of SUDS students is hard at work improving and extending the machine-learning risk model this semester, to take this project in exciting new directions! This involves, for instance, finding and integrating additional publicly available civic data on the City of Pittsburgh area, such as, for instance, unpaid tax liens, smoke alarm data, 311 data, and others. Students are also engaged in conducting a post-hoc evaluation of the deployed risk model. Now that it has been generating risk scores for the last few months, how accurate are those? How successful are they at leading to increased number of fire risk violations being caught?
- Prior machine learning experience strongly preferred; prior experience with models used in production contexts is even more beneficial.