Ensemble Methods in Ordinal Data Classification

Ordinal classification problems can be found in various areas, such as product recommendation systems, intelligent health systems and image recognition. These problems have the goal of learn-ing how to classify certain instances (e.g. a movie) in an ordinal scale (e.g. good, average, bad). The performance of supervised learned problems (such as ordinal classification) can be im-proved by using ensemble methods, where various models are combined to perform better deci-sions. While there are various ensemble methods for nominal classification, ranking and regres-sion, ordinal classification has not received the same level of attention. The goal of this dissertation is, therefore, to introduce novel ensemble methods for the classi-fication of ordinal data. To do this, first a new ordinal classification algorithm based on decision trees and the data replication method is presented, whose results show a competitive performance when compared to other ordinal and non-ordinal classifiers. Then, the main ideas of this method are exploited to try and improve ensembles whose models share similarities with decision trees (i.e. ADABOOST with Decision Stumps and Random Forests). i i