LAUSR

Lots of real-world problems require multiclass classification. Since most general classification methods are originally introduced for binary problems (including two classes), they should be extended to multiclass problems. A solution proposed for multiclass problems is to decompose such problems to several binary ones and then combine the results obtained from smaller problems as a tree-based structure to obtain the final solution. In this study, a novel method which uses VlseKriterijumska optimizacija I Kompromisno Resenje multi-criteria decision-making was proposed to build the best directed binary tree with minimum error. The proposed method is independent of classifier; nevertheless, in the current experiments, the support vector machine was employed as the base classifier. The proposed method was tested on datasets and the results were compared with other methods. It can be seen that it improves precision of predictions significantly.