“…In turn, our results show greater robustness than those obtained in [19] in which it was possible to obtain values of accuracy, precision, recall and F1 score of 87.44%, 52.84%, 50.68% and 51.73% respectively, to be applied in predicting students graduating on time. This affirmation can be sustained in the study of [29] where it is pointed out that these metrics reflect a high capacity of the classification model, because, the greater the recall, the greater the capacity of the model to recognize positive instances, the greater the Whatever the accuracy, the capacity of the model to distinguish instances will be reflected, finding the F1 score as the combination of the two metrics, in this sense, the higher the F1 score, the more solid the classification model will be. Validated the use of the SVM Quadratic algorithm in the predictive model of the satisfaction of university students, the classification model is evaluated by means of the receiver operating characteristic curve (ROC) technique, which allows us to visualize the balance between the rate of true positives (TPR) and the false negative rate (FNR).…”