Abstract
This paper reports on an empirical investigation into the ability of Artificial Neural Network (ANN) technique in learning and predicting preference. ANNs were used to learn preference patterns of holistic judgments on a sample of multi-criteria decision alternatives defined by the orthogonal design. Then a comparative study was conducted with utility theory-based models and ANNs to predict decision makers’ choice. In all cases, the predictive ability of ANN was found to be as good as or better than those of utility theory-based models.
Recommended Citation
Nguyen, Dat-Dao and Kira, Dennis, "On Learning and Predicting Preference with Artificial Neural Networks: Some Preliminary Results" (1998). AMCIS 1998 Proceedings. 67.
https://aisel.aisnet.org/amcis1998/67