Search

The objective of this research was to develop robust predictive models of the gains in working memory (WM) and fluid intelligence (Gf) following executive attention training in children, using genetic markers, gender, and age variables. We explore the influence of genetic variables on individual differences in susceptibility to intervention. Sixty-six children (males: 54.2%) aged 50.9-75.9 months participated in a four-weeks computerized training program. Information on genes involved in the regulation of dopamine, serotonin, norepinephrine, and acetylcholine was collected. The standardized pre- to post-training gains of two dependent measures were considered: WM Span backwards condition (WISC-III) and the IQ-f factor from the Kaufman Brief Intelligence Test (K-BIT). A machine-learning methodology was implemented utilizing multilayer perceptron artificial neural networks (ANN) with a backpropagation algorithm. Both ANN models reached high overall accuracy in their predictive classification. Variations in genes involved in dopamine and norepinephrine neurotransmission affect children's susceptibility to benefit from executive attention training, a pattern that is consistent with previous studies.

Predicting and understanding different key outcomes in a student's academic trajectory such as grade point average, academic retention, and degree completion would allow targeted intervention programs in higher education. Most of the predictive models developed for those key outcomes have been based on traditional methodological approaches. However, these models assume linear relationships between variables and do not always yield accurate predictive classifications. On the other hand, the use of machine-learning approaches such as artificial neural networks has been very effective in the classification of various educational outcomes, overcoming the limitations of traditional methodological approaches. In this study, multilayer perceptron artificial neural network models, with a backpropagation algorithm, were developed to classify levels of grade point average, academic retention, and degree completion outcomes in a sample of 655 students from a private university. Findings showed a high level of accuracy for all the classifications. Among the predictors, learning strategies had the greatest contribution for the prediction of grade point average. Coping strategies were the best predictors for degree completion, and background information had the largest predictive weight for the identification of students who will drop out or not from the university programs.

Many studies have explored the contribution of different factors from diverse theoretical perspectives to the explanation of academic performance. These factors have been identified as having important implications not only for the study of learning processes, but also as tools for improving curriculum designs, tutorial systems, and students' outcomes. Some authors have suggested that traditional statistical methods do not always yield accurate predictions and/or classifications (Everson, 1995; Garson, 1998). This paper explores a relatively new methodological approach for the field of learning and education, but which is widely used in other areas, such as computational sciences, engineering and economics. This study uses cognitive and non-cognitive measures of students, together with background information, in order to design predictive models of student performance using artificial neural networks (ANN). These predictions of performance constitute a true predictive classification of academic performance over time, a year in advance of the actual observed measure of academic performance. A total sample of 864 university students of both genders, ages ranging between 18 and 25 was used. Three neural network models were developed. Two of the models (identifying the top 33% and the lowest 33% groups, respectively) were able to reach 100% correct identification of all students in each of the two groups. The third model (identifying low, mid and high performance levels) reached precisions from 87% to 100% for the three groups. Analyses also explored the predicted outcomes at an individual level, and their correlations with the observed results, as a continuous variable for the whole group of students. Results demonstrate the greater accuracy of the ANN compared to traditional methods such as discriminant analyses. In addition, the ANN provided information on those predictors that best explained the different levels of expected performance. Thus, results have allowed the identification of the specific influence of each pattern of variables on different levels of academic performance, providing a better understanding of the variables with the greatest impact on individual learning processes, and of those factors that best explain these processes for different academic levels.