Disabilities can unfairly limit the academic achievement of students when protocols are not put in place to offset its impact. The WHODAS 2.0 is a tool that can measure impairments related to such disabilities. Using machine learning algorithms such as decision trees and the support vector machines, we aimed to use the responses to WHODAS 2.0 to predict the proper set of accommodations. In this paper, we demonstrate that while both models can adequately predict several accommodations, the decision tree outperformed the support vector machine in its overall precision and recall of those accommodations. Therefore, the information within the WHODAS 2.0 contains some predictive capacity in the assignment of accommodations to help with the disability of the student.