The processes used in identifying/diagnosing specific learning disabilities (SLDs) vary across settings and classification systems. Moreover, the theoretically and mathematically derived identification models (i.e., discrepancy model) have thus far not demonstrated adequate reliability and validity. The present study explores the utility of machine learning models in the identification/diagnosis of SLDs. Five different classification models are trained using a dataset made up of two sources: a subset of the norming sample of the Woodcock-Johnson Tests of Cognitive Abilities, Achievement, and Oral Language (n > 3,500), and a subset of a diagnostic clinic's internal database from the University of Colorado (n > 600). The study demonstrates the performance of both supervised and unsupervised machine learning models. Classification accuracy (sensitivity/specificity) for each model is described and performance across models is compared. Model performance is compared to existing identification/diagnosis models. Conclusions, implications, and future directions are discussed. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com.bibliotheek.ehb.be/en-US/products/dissertations/individuals.shtml.]