Classification model for student dropouts using machine learning: A case study

Information and communication technologies have been fulfilling a highly relevant role in the different fields of knowledge, addressing problems various disciplines; there is an increased capacity to identify patterns anomalies organization's data using mining; In this context, study aimed develop classification model for student dropout, applying machine learning with autoML method H2O.ai framework; dimensionality socioeconomic academic characteristics has taken into account, purpose that directors make reasonable decisions counteract abandonment students programs. The methodology used was technological type, purposeful level, incremental innovation, temporal scope, synchronous; collection prospective. For this, 20-item questionnaire applied 237 enrolled master's degree programs education Graduate School. research resulted supervised model, Gradient Reinforcement Machine (GBM), classify thus identifying main associated factors influence obtaining Gini coefficient 92.20%, AUC 96.10% LogLoss 24.24% representing efficient performance.