The Predicting Academic Performance in University Students Using Machine Learning
Ernesto Bolaños-Rodríguez,
Cristina Flores-Amador,
Asdrúbal López-Chau,
Alonso Ernesto Solis-Galindo,
Antonio Zárate-Rosas
Affiliations
Ernesto Bolaños-Rodríguez
Escuela Superior de Tizayuca-Universidad Autónoma del Estado de Hidalgo. Carretera Federal Tizayuca-Pachuca Km 2.5. 43800. Tizayuca, Estado de Hidalgo, México.
Cristina Flores-Amador
Escuela Superior de Tizayuca-Universidad Autónoma del Estado de Hidalgo. Carretera Federal Tizayuca-Pachuca Km 2.5. 43800. Tizayuca, Estado de Hidalgo, México.
Asdrúbal López-Chau
Centro Universitario UAEM Zumpango, Universidad Autónoma del Estado de México, 55600, México.
Alonso Ernesto Solis-Galindo
Escuela Superior de Tizayuca-Universidad Autónoma del Estado de Hidalgo. Carretera Federal Tizayuca-Pachuca Km 2.5. 43800. Tizayuca, Estado de Hidalgo, México.
Antonio Zárate-Rosas
Escuela Superior de Tizayuca-Universidad Autónoma del Estado de Hidalgo. Carretera Federal Tizayuca-Pachuca Km 2.5. 43800. Tizayuca, Estado de Hidalgo, México.
In the present research, the prediction of the academic performance of university students of an undergraduate educational program is carried out by applying Machine Learning (ML) with the purpose of determining the students with academic difficulties and excellence in school performance. It is an applied research in a population of 327 students, to which a representative sample of 74 students is determined, using a proportional stratified probability sampling, in which the stratum is the semester the student is studying out of the nine that make up the study plan. The work is an applied study with a pre-experimental design of a single group, because after applying ML the results are observed and the measurements is carried out. The main conclusions obtained allow establishing a methodology for the application of ML methods in the prediction of academic performance. The best performing algorithms used are Support Vector Machine (SVM) and Neural Network (NN).
