Resumen de Predicción del Fracaso Escolar Mediante Técnicas de Minería de Datos

C. Márquez Vera, C. Romero, Sebastián Ventura Soto

• This paper proposes to apply data mining techniques to predict school failure and drop out. We use real data on 670 middle-school students from Zacatecas, México and employ white-box classification methods such as induction rules and decision trees. Experiments attempt to improve their accuracy for predicting which students might fail or drop out by: firstly, using all the available attributes; next, selecting the best attributes; and finally, rebalancing data, and using cost sensitive classification. The outcomes have been compared and the best resulting models are shown.