Data Scientist

About Trust Neighborhoods:
Trust Neighborhoods is a non-profit dedicated to helping neighborhoods fight displacement and drive their own investment. Core to Trust Neighborhoods’ work is creating the Mixed-Income Neighborhood Trust (MINT) model. Trust Neighborhoods supports neighborhood-based organizations in launching MINTs that use outside investment to create and own high-quality, affordable rental housing and retail. Trust Neighborhoods created the MINT model in 2020, launched two MINTs in 2021, and is now beginning to work nationally.

About the Role:
Trust Neighborhoods is seeking a Data Scientist to help the team use data to better identify, underwrite, market, and evaluate MINTs.

Specifically, this individual will:
-Identify and build datasets related to real estate dynamics (e.g., home value changes, rent changes, vacancy) and neighborhood characteristics (e.g., median household income, demographics)
-Build a model for identifying and categorizing gentrification pressures at the neighborhood-level
-Create a process for incorporating data into various stages of the MINT process
-Set-up a dashboard for ongoing evaluation of MINTs
-Help the Trust Neighborhoods team better define the scope of its data needs

Experience and qualifications:
-Experience building and cleaning datasets by scraping and combining disparate data sources
-Experience creating models to interrogate datasets and inform future decision-making
-A strong ability to communicate data findings to technical and non-technical audiences
-Interest in urban development and/or affordable housing preferred
Experience with ArcGIS or other mapping software is a positive, but is not required

Salary & logistics:
Part-time role in the winter or spring, or full-time role in the summer
Based in Kansas City, MO or remote
Stipend, hourly, or pro-rated annual salary as options

Application process:
Please email resume and a short description of your interest to natalie.gauger@trustneighborhoods.com. Applications will be reviewed on a rolling basis.