Examinando por Materia "Icetex"

Mostrando 1 - 1 de 1
  • No hay miniatura disponible
    Ítem
    Determinantes del riesgo de incumplimiento en créditos educativos : un análisis para Colombia
    (Universidad EAFIT, 2020) Granda Rodríguez, Manuela Andrea; Posso Suárez, Christian Manuel
    This document uses non-parametric Machine Learning methodologies, in particular the XGBoost algorithm, to predict the risk of non-compliance with educational credits in Colombia offered by ICETEX between 2015 and 2018. The interest variable is the risk of default in student credits and is used as variable determinants associated with the socioeconomic level of students, as well as school information and academic achievement for each student. The main results show that socioeconomic variables with very good default predictors, in particular variables such as parent education and scores on critical reading tests are strong predictors. The results found contribute to economic and social policy decisions on the design of methods for higher education coverage through meritorious credits with public and private funds.