Using Decision Trees for Predicting Academic Performance Based on Socio-Economic Factors

The main objective of this research study is to determine how socio-economic factors affect the educational attainments of high-school students. For our study, we considered the socio-economic and academic data corresponding to more than ten years of records obtained from the leading university of an Andean country. Then, we used classification algorithms and machine learning techniques to determine which factors are the more influential on academic performance. We found that academic scholarship, age, county and high school degree influences academic performance of students. The results of this study constitute important information for academic directors and social workers involved in the task of improving the conditions of students and providing all of them the means to success.