The Best Thresholds for Rapid Identification of Episodic and Chronic Homeless Shelter Use

Abstract

This paper explores how to best identify clients for housing services based on their homeless shelter access patterns. We utilize the number of shelter stays and episodes of shelter use for a client within a specified time window. Thresholds are then applied to these values to determine if that individual is a good candidate for housing support. Using new housing referral impact metrics, we explore a range of threshold and time window values to determine which combination both maximizes impact and identifies good candidates for housing as soon as possible. New insights are also provided regarding the characteristics of the “under-the-radar” client group who are typically not identified for housing support.

A Rule Search Framework for the Early Identification of Chronic Emergency Homeless Shelter Clients

“…This shortcoming can be addressed by applying the techniques in this paper to a data set that has been augmented to include individuals sleeping outside, possibly using input from street outreach teams. Cluster analysis has previously demonstrated that the client shelter access patterns in the DI data set are broadly representative of most North American emergency shelters [25]. While the rules presented in this paper should be a reasonable starting place for most shelters, it is still best for each shelter seeking to apply our techniques to first conduct a new rule search on their own client data.…”

“…This makes them much easier to implement using a database interface that supports basic thresholding and logical operators. While work has previously been done exploring threshold testing for chronic shelter use identification [25,26], this work lacks the rigor of a formalized rule search framework that optimizes rule selection based on a performance metric.…”