The school-dropout problem is a serious issue that affects both a country’s education system and its economy, given the substantial investment in education made by national governments. One strategy for counteracting the problem at an early stage is to identify students at risk of dropping out. The present study introduces a model to predict student dropout rates in the Escuela Politécnica Nacional leveling course. Data related to 2097 higher education students were analyzed; a logistic regression model and an artificial neural network model were trained using four variables, which incorporated student academic and socio-economic information. After comparing the two models, the neural network, with an experimentally defined architecture of 4–7–1 architecture and a logistic activation function, was selected as the model that should be applied to early predict dropout in the leveling course. The study findings show that students with the highest risk of dropping out are those in vulnerable situations, with low application grades, from the Costa regime, who are enrolled in the leveling course for technical degrees. This model can be used by the university authorities to identify possible dropout cases, as well as to establish policies to reduce university dropout and failure rates.

Universities are committed to offering quality education; however, a high rate of academic failure is often observed in the first year of studies. Considering the impact that motivation and emotional aspects can have on students’ commitment to study and therefore on their academic performance, achievement, and well-being, this study aims to identify the factors associated with academic success or failure in 1071 students entering the National Polytechnic School (Quito, Ecuador). The data were compiled from the existing computer records of the university with the permission of the responsible administrative staff. A predictive model has been used and a binary logistic regression analysis was carried out through the step-forward regression procedure based on the Wald statistic to analyze the predictive capacity of the variables related to emotional intelligence, motivational and self- regulated socio-cognitive skills, goal orientation, and prior academic achievement (measured by university entrance marks and through a knowledge test carried out at the beginning of the university academic year). To determine the cut-off point for the best discriminatory power of each of the variables, a Receiver Operating Characteristics (ROC) curve analysis has been used. The results indicate that the variables that are significant in the prediction of academic success or failure are the two academic performance measures: the emotional attention variable, and the performance-approach goals and the motivational self-efficacy variable. Additionally, the highest predictive power is displayed by the prior academic performance measure obtained through the knowledge test conducted at the beginning of the university course.

The purpose of this study is to train an artificial neural network model for predicting student failure in the academic leveling course of the Escuela Politécnica Nacional of Ecuador, based on academic and socioeconomic information. For this, 1308 higher education students participated, 69.0% of whom failed the academic leveling course; besides, 93.7% of the students self-identified as mestizo, 83.9% came from the province of Pichincha, and 92.4% belonged to general population. As a first approximation, a neural network model was trained with twelve variables containing students’ academic and socioeconomic information. Then, a dimensionality reduction process was performed from which a new neural network was modeled. This dimension reduced model was trained with the variables application score, vulnerability index, regime, gender, and population segment, which were the five variables that explained more than 80% of the first model. The classification accuracy of the dimension reduced model was 0.745, while precision and recall were 0.883 and 0.778, respectively. The area under ROC curve was 0.791. This model could be used as a guide to lead intervention policies so that the failure rate in the academic leveling course would decrease.

This work validates a teaching evaluation instrument applied to professors in engineering, sciences and higher technological level programs of the Escuela Politécnica Nacional, using the method of Factor Analysis with extraction of principal components. The database used for the research was previously examined and refined due to inconsistency, eg. outliers, out of range values, etc. The result of the method described above was a reduced survey of 15 items, which was obtained from an original study of 33 items. This new questionnaire clearly identifies the four main dimensions or aspects required: teaching development and planning, teacher-student relationship, evaluation, and a global assessment question. The reduction of the evaluation scale will allow to improve the process of  integral teaching performance evaluation of the faculty at Escuela Politécnica Nacional, and this method could serve as a benchmark for the teaching evaluation process of other universities that belong to the higher education system of Ecuador.

A model was developed to measure general studies based upon the Consejo de Evaluación, Acreditación y Aseguramiento de la Calidad de la Educación Superior (CEAACES), the same structure that is used based upon international guidelines, in such a way to successfully meet the accreditation process for engineering and science tracks within the Escuela Politécnica Nacional (EPN) (National Polytechnic School). This instrument contemplates the selection of students who have completed a minimum of 150 credits in order to evaluate the result of teaching by testing levels of competency in general studies, whose results can serve as a guide for the decision makers.