The Nataf-Beta Random Field Classifier: An Extension of the Beta Conjugate Prior to Classification Problems
This provides a general-purpose classification method for real-continuous and real-integer attribute problems, but it is incremental as it builds on existing Beta prior concepts without surpassing state-of-the-art performance.
The paper tackles classification problems by extending the Beta conjugate prior to a discriminative approach called the Nataf-Beta Random Field Classifier, which models class probabilities with Beta-distributed marginals and random field parameters, achieving top-tier accuracy on six benchmark datasets without statistically outperforming the best reported results.
This paper presents the Nataf-Beta Random Field Classifier, a discriminative approach that extends the applicability of the Beta conjugate prior to classification problems. The approach's key feature is to model the probability of a class conditional on attribute values as a random field whose marginals are Beta distributed, and where the parameters of marginals are themselves described by random fields. Although the classification accuracy of the approach proposed does not statistically outperform the best accuracies reported in the literature, it ranks among the top tier for the six benchmark datasets tested. The Nataf-Beta Random Field Classifier is suited as a general purpose classification approach for real-continuous and real-integer attribute value problems.