Comparative study of artificial neural network and statistical models for predicting student grade point averages

摘要: Abstract This paper compares linear regression; stepwise polynomial and fully-connected, single middle layer artificial neural network models with an index used by admissions committee for predicting student GPAs in professional school. It also provides methods implementing, interpreting, evaluating networks, including optimization of model structure simple networks. While the identifies additional over regression models, none empirical was statistically significantly better than practitioners' index.