Learning to Predict Transitions within the Homelessness System from Network Trajectories

Abstract

This study infers the unobserved underlying network of homeless services from administrative data collected by homeless service providers. Both the structure of the inferred network, and historical observations, are used to identify individuals with similar trajectories so that their next assignments can be predicted. Experimental evaluation shows that the proposed approach performs well not only on predicting exit from the system, or simply guessing high frequency services (as most baselines), but is also successful in less frequent scenarios.