Main influential factors in academic performance. Analysis from data mining

Abstract

The objective of this article is to analyze the impact of a series of independent variables on the academic performance of an undergraduate student. A database is constructed with one dependent variable (average) and 23 independent variables: age, school, scholarship, occupation, income, transportation, housing, mother’s education level, father’s education level, number of siblings, parent’s marital status, mother’s occupation, father occupation, weekly study hours, non-scientific books read per year, scientific books read per year, class attendance, exam preparation, study method, class notes, attention in class, course participation, economic level. Subsequently, using machine learning and data mining software (WEKA) and applying intelligent techniques, a statistical selection and classification process is conducted to determine the most influential independent variables on the dependent variable. As a result of this process, it is found that, with effectiveness more significant than 81%, the most influential independent variables on the dependent variable, in order of importance, are the mother’s education level, father’s education level, and class notes. Other factors, such as base tuition scores and income (socioeconomic indicators), were less significant.