Algorithms are becoming prevalent but are often opaque and need external validation to assess whether or not they meet their purported objectives. The purpose of this study is to validate, using the limited information available, the algorithm used by the National Resident Matching Program (NRMP) whose intention is to match applicants to medical residencies based on applicants’ prioritized preferences. The methodology involved first using randomized computer-generated data to overcome the inaccessible proprietary data on applicant and program rankings. Simulations using these data were run through the compiled algorithm’s procedures to obtain match outcomes. The study’s findings are that the current algorithm’s matches are related to program input but not to applicant input, the applicant’s prioritized ranking of programs. A modified algorithm with student input as the primary factor is then developed and run using the same data, resulting in match outcomes that are related to both applicant and program inputs, improving equity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.