Deep Learning in Predicting High School Grades: A Quantum Space of Representation

This paper applies deep learning to the prediction of Portuguese high school grades. A multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is demonstrate adequacy as quantitative explanatory paradigm when compared with classical econometrics approach. results encompass point predictions, intervals, variable gradients, impact an increase in class size on Deep learning’s generalization error lower student grade prediction, its intervals more accurate. gradient empirical distributions largely align coefficient estimates, indicating satisfactory fit. Based discrepancies, student’s mother being employer does not seem be positive factor. benign shift concerning balance between home career affairs for both genders should reinforced. broadens spectrum possibilities, providing quantum solution hinged universal approximator. In case academic achievement-critical factor such size, where literature neither unanimous importance nor direction, formed three distinct clusters per individual signals. Doi: 10.28991/ESJ-2022-SIED-012 Full Text: PDF