Grupo UTN GIESIN - Difusión Científica - Artículos de Revista
Permanent URI for this collectionhttp://48.217.138.120/handle/20.500.12272/681
Browse
Item Academic performance profiles : a descriptive model based on data mining(2015-03-10) La Red Martínez, David Luis; Karanik, Marcelo; Giovaninni, Mirta Eve; Pinto, NoeliaAcademic performance is a critical factor considering that poor academic performance is often associated with a high attrition rate. This has been observed in subjects of the first level of Information Systems Engineering career (ISI) of the National Technological University, Resistencia Regional Faculty (UTN-FRRe), situated in Resistencia city, province of Chaco, Argentine. Among them is Algorithms and Data Structures, where the poor academic performance is observed at very high rates (between 60% and about 80% in recent years). In this paper, we propose the use of data mining techniques on performance information for students of the subject mentioned, in order to characterize the profiles of successful students (good academic performance) and those that are not (poor performance). In the future, the determination of these profiles would allow us to define specific actions to reverse poor academic performance, once detected the variables associated with it. This article describes the data models and data mining used and the main results are also commentedItem Perfiles de rendimiento académico : un modelo basado en minería de datos(2015-03-01) La Red Martínez, David Luis; Karanik, Marcelo; Giovaninni, Mirta Eve; Pinto, NoeliaEl rendimiento académico es un factor crítico teniendo en cuenta que, frecuentemente, el bajo rendimiento académico está asociado a una alta tasa de deserción. Esto se ha observado en asignaturas del primer nivel de la carrera de Ingeniería en Sistemas de Información (ISI) de la Universidad Tecnológica nacional facultad Regional Resistencia (UTn-fRRe), situada en la ciudad de Resistencia, provincia del Chaco, Argentina, entre ellas Algoritmos y Estructura de datos, donde el bajo rendimiento académico se observa en proporciones muy altas (entre el 60% y el 80% aproximadamente en los últimos años). En este trabajo se propone la utilización de técnicas de minería de datos sobre información del desempeño de los alumnos de la asignatura mencionada con el propósito de caracterizar los perfiles de alumnos exitosos (buen rendimiento académico) y de aquellos que no lo son (bajo rendimiento académico). La determinación de estos perfiles permitiría a futuro definir acciones específicas tendientes a revertir el bajo rendimiento académico, una vez detectadas las variables asociadas al mismo. En este artículo se describen los modelos de datos y de minería de datos utilizados y se comentan los principales resultados obtenidosItem Towards to a predictive model of academic performance using data mining in the UTN-FRRe(2016-05-02) La Red Martínez, David Luis; Karanik, Marcelo; Giovaninni, Mirta Eve; Scappini, ReinaldoStudents completing the courses required to become an Engineer in Information Systems in the Resistencia Regional Faculty, National Technological University, Argentine (UTN-FRRe), face the challenge of attending classes and fulfilling course regularization requirements, often for correlative courses. Such is the case of freshmen's course Algorithms and Data Structures: it must be regularized in order to be able to attend several second and third year courses. Based on the results of the project entitled “Profiling of students and academic performance through the use of data mining”, 25/L059 - UTI1719, implemented in the aforementioned course (in 2013-2015), a new project has started, aimed to take the descriptive analysis (what happened) as a starting point, and use advanced analytics, trying to explain the why, the what will happen, and how we can address it. Different data mining tools will be used for the study: clustering, neural networks, Bayesian networks, decision trees, regression and time series, etc. These tools allow different