Comparison of matlab and spss software in the prediction of academic achievement with artificial neural networks: modeling for elementary school students

In this study, it was aimed to compare the predictions of the academic achievement of theartificial neural networks (ANN) run in MATLAB and SPSS software and to determine thefactors related to their academic achievement. Sample consisted of 465 students who werestudying at Grade 4 in primary schools in the Central Anatolian Region of Turkey in 2017. A12-questions questionnaire was used as the collection tool. For the content validity of thequestionnaire, expert opinions were received. The KR20 reliability coefficient was calculatedas .60. An exploratory factor analysis was run for the construct validity. In the ANN model, theitems related to the academic achievement in the questionnaire were considered as independentvariables / inputs, and the academic achievements of the previous year as the dependentvariables / outputs. The predictions of the academic achievement of the ANN models wereanalyzed in MATLAB R2013a and SPSS 24.0 software and the regression coefficients of theindependent variables were examined. It was found that MATLAB software had a higher rateof the correct prediction compared to SPSS. In the regression coefficients of the independentvariables, some differences and similarities between the results of MATLAB and SPSS werefound.