UW Data Science Seminar: Data Science for Social Good

When

10/01/2024    
4:30 pm – 5:20 pm

Where

Please join us for a UW Data Science Seminar event on Tuesday, October 1st from 4:30 to 5:20 p.m. PDT. The seminar will feature two projects from this past summer’s UW Data Science for Social Good program.

The seminar will be held in the Physics/Astronomy Auditorium (PAA), Room A118 – campus map.

 

“Investigating Transit Equity Through ORCA Fare Card Analysis”

Team Project Leads: Mark Hallenbeck, [Retired] Director of the Washington State Transportation Center (TRAC), University of Washington, and Ryan Avery, Deputy Director of the Washington State Transportation Center (TRAC), University of Washington.
Data Science Mentor: Bryna Hazelton, eScience Institute, University of Washington
Student Fellows: Rebecca Hayes, Himanshu Jaikumar Naidu, Siman Ning, Ishan Saksena

Abstract:

Transit service is a public good, that is essential for improving access to opportunities, especially transit-dependent populations. Transit agencies typically lack knowledge about transit usage patterns. Transit fare card data describes actual transit use. Analyzing fare card data, can help identify service gaps and inequities, guiding improvements to enhance service quality, increase ridership, and reduce environmental impacts.

This project analyzes fare card data from the ORCA system used in the Puget Sound region of Washington State. ORCA data, which includes different fare card classes, enables the analysis of transit usage among priority groups, such as people with low-income or disabilities. By examining actual transit use of anonymized riders against geographic and demographic characteristics, this project identifies where transit system improvements need to be made to improve the quality of services being provided, with emphasis on demographic populations most dependent on transit.

 

“Understanding Unsheltered Homelessness in King County: UW 2023 Seattle Area Homeless Count”

Team Project Lead: Zach Almquist, Associate Professor, Department of Sociology, University of Washington
Data Science Mentor: June Yang, eScience Institute, University of Washington
Student Fellows: Brooke Kaye, Felix Jr. Appiah Kubi, Jessica Robinson, Rebecca Schachtman

Abstract:

The US Department of Housing and Urban Development released the 2023 Annual Homeless Assessment Report (AHAR) on December 15, 2023. The report estimates that 653,100 people in the U.S. experienced homelessness in 2023, a 12% increase from 2022. This estimate comes from the Point-in-Time (PIT) count conducted on a single night in January over communities across the US. The PIT, which is mandated by HUD every two years, is composed of two key elements: (1) the emergency shelter report from administrative records and (2) the unsheltered PIT count typically performed on a single night in January through volunteers walking around the community and tabulating how many people they see. This so-called “visual census” of unsheltered people experiencing homelessness has a number of issues, from methodology (people are undercounted for a number of reasons) to ethics (people don’t get a voice in how they are counted). In other words, there is much room for improvement in understanding our unhoused neighbors.

A team at UW led by Dr. Zack Almquist has been working with the King County Regional Homelessness Authority since 2022 to improve the unsheltered PIT methodology and accompanying demographic and needs assessment surveys. In 2022, the University of Washington and KCRHA implemented a novel, network-based method for counting the unsheltered people experiencing homelessness known as Respondent-Driven Sampling. That was followed by a larger pilot study conducted in 2023, resulting in a dataset containing rich network and demographic information from 1,100+ sheltered and unsheltered people.

This year’s DSSG project finalized the 2023 data set and conducted analyses to better understand the needs of people experiencing homelessness. The team produced data summaries, policy reports, and created an this website to host the findings and describe the method for other communities to use.