Using Decision Trees to Predict Critical Reading Performance.

In Colombia, all undergraduate students, regardless of the professional training program they take, must complete general competencies sections Saber Pro exam that include Critical Reading, Quantitative Reasoning, Citizen Competencies, Written Communication, and English. This paper presents application classification technique based on decision trees in prediction performance Reading section presented by students Pontificia Universidad Javeriana Cali years 2017 2018. The CRISP methodology was used. From socioeconomic, academic institutional data stored ICFES databases, a repository built, cleaned transformed. A mineable view composed 2052 records 17 attributes obtained. J48 algorithm Weka tool used to build tree. score obtained taken as class. According results obtained, Philosophy, Applied Mathematics, Medicine programs stood out for having best this test. Among predictive variables associated with skill are faculty, age group student's transportation index, three important related good or low Cali. knowledge generated research is constituted quality information support decision-making process university directives order improve higher education offered institution.