Artificial neural systems as a research paradigm for the study of group decision support systems

Artificial neural systems (ANSs) have received interest recently because of their ability to accurately forecast and classify data. Group decision support systems (GDSSs) also have received much interest ibr their support of group communication and decision making. This paper explores the potential of the ANS as a methodology for modeling the many complex, interrelated research variables involved in the field of GDSS. As an illustration, multilinear regression, an ANS with backpropagation, and an ANS with a genetic algorithm were developed to classify 133 subjects into verbal or GDSS groups based on their responses to a questionnaire. The ANSs with backpropagation and the genetic algorithm achieved higher classification accuracies (81.8 and 90.9%, respectively) than was achieved with multilinear regression (75.8%). Therefore, an ANS may more accurately model the many interrelationships occurring with GDSS group behavior.