Client Team: Dr. Tom Byrne Associate Professor, School of Social Work, BU Dr. Molly Richard Postdoctoral Associate, Center for Innovation in Social Science, BU
Instructor: Prof. Thomas Gardos
Technical Project Manager (TPM): Dhruv Shah Project Manager (PM): Jasmine Dong
Team Members: Syeda Shehrbano Aqeel (team lead) Samritha Aadhi Ravikumar Kunshu Yang Renjie Fan Shiheng Xu
Goal: Develop a predictive model of homelessness at the community level using data from 2007-2023. Focuses on approximately 400 Continuums of Care (CoC) that receive federal homeless assistance funding from the U.S. Department of Housing and Urban Development (HUD). Unique Focus: Unlike previous studies that predict homelessness at the individual level, this project centers on community-level factors.
Primary Data: Annual homelessness counts from HUD across CoC units. Additional Data: Publicly available community-level factors such as rent rates, demographic and economic conditions, aggregated by CoC. Timeframe: 2007 to 2023.
Moving beyond simply identifying associations between community-level factors and homelessness. Objective: Predict the number or rate of homelessness in each CoC based on structural determinants like rent levels and economic conditions.
Modeling Approach: Regression models or other predictive machine learning techniques. Required Skills: Familiarity with regression models, feature engineering, and experience with the pandas and scikit-learn packages in Python.
Create a new branch from dev, add changes on the new branch you just created. Open a Pull Request to dev. Add your PM and TPM as reviewers. At the end of the semester during project wrap up open a final Pull Request to main from dev branch.