Can Machine Learning Create an Advocate for Foster Youth?

TL;DR

This paper explores how machine learning can enhance support services for foster youth transitioning to independence by providing personalized resources and aiding caseworkers in their efforts.

Contribution

It introduces a machine learning algorithm integrated into the Think of Us platform to personalize aid and improve resource allocation for foster youth.

Findings

Algorithm effectively collates relevant data for youth needs

Supports caseworkers with targeted resource recommendations

Enhances personalized assistance for foster youth

Abstract

Statistics are bleak for youth aging out of the United States foster care system. They are often left with few resources, are likely to experience homelessness, and are at increased risk of incarceration and exploitation. The Think of Us platform is a service for foster youth and their advocates to create personalized goals and access curated content specific to aging out of the foster care system. In this paper, we propose the use of a machine learning algorithm within the Think of Us platform to better serve youth transitioning to life outside of foster care. The algorithm collects and collates publicly available figures and data to inform caseworkers and other mentors chosen by the youth on how to best assist foster youth. It can then provide valuable resources for the youth and their advocates targeted directly towards their specific needs. Finally, we examine machine learning as a support system and aid for caseworkers to buttress and protect vulnerable young adults during their transition to adulthood.