SmartChoice: An Online Recommender System to Support Low-Income Families in Public School Choice
Public school choice at the primary and secondary levels is a keyelement of the U.S. No Child Left Behind Act of 2001 (NCLB). If aschool does not meet assessment goals for two consecutive years, bylaw the district must offer students the opportunity to transfer to aschool that is meeting its goals. Making a choice with such potentialimpact on a child's future is clearly monumental, yet astonishinglyfew parents take advantage of the opportunity. Our research has shownthat a significant part of the problem arises from issues ininformation access and information overload, particularly for lowsocioeconomic status families. Thus we have developed an online,content-based recommender system, called SmartChoice. Itprovides parents with school recommendations for individual studentsbased on parents' preferences and students' needs, interests,abilities, and talents. The first version of the online applicationwas deployed and live for focus group participants who used it for theJanuary and March/April 2008 Charlotte-Mecklenburg school choiceperiods. This article describes the SmartChoice Program and theresults of our initial and followup studies with participants.
recommender systems; user modeling; public school choice
Copyright © 2015, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.