Predictors of Re-admission for Homeless Families in New York City: The Case of the Win Shelter Network

TL;DR

This study integrates shelter and city data to predict re-admission of homeless families in NYC, aiming to improve shelter services and develop data-driven 'smart shelters'.

Contribution

It introduces a unified dataset and a preliminary classification model to predict re-entry risk for homeless families, enhancing operational efficiency.

Findings

Integrated datasets enable comprehensive analysis.

Preliminary model predicts re-admission likelihood.

Insights support development of data-driven shelter strategies.

Abstract

New York City faces the challenge of an ever-increasing homeless population with almost 60,000 people currently living in city shelters. In 2015, approximately 25% of families stayed longer than 9 months in a shelter, and 17% of families with children that exited a homeless shelter returned to the shelter system within 30 days of leaving. This suggests that "long-term" shelter residents and those that re-enter shelters contribute significantly to the rise of the homeless population living in city shelters and indicate systemic challenges to finding adequate permanent housing. Women in Need (Win) is a non-profit agency that provides shelter to almost 10,000 homeless women and children (10% of all homeless families of NYC), and is the largest homeless shelter provider in the City. This paper focuses on our preliminary work with Win to understand the factors that affect the rate of readmission of homeless families at Win shelters, and to predict the likelihood of re-entry into the shelter system on exit. These insights will enable improved service delivery and operational efficiencies at these shelters. This paper describes our recent efforts to integrate Win datasets with city records to create a unified, comprehensive database of the homeless population being served by Win shelters. A preliminary classification model is developed to predict the odds of readmission and length of shelter stay based on the demographic and socioeconomic characteristics of the homeless population served by Win. This work is intended to form the basis for establishing a network of "smart shelters" through the use of data science and data technologies.