Fusing absolute and relative information for augmenting the method of nearest neighbors for ordinal classification

Mengzi Tang, Raúl Pérez-Fernández, Bernard De Baets

Abstract: Highlights•Ordinal classification could benefit from the use of available relative information•The idea behind k nearest neighbors can be translated from absolute to relative information•Relative information can make up for the lack of absolute information•Increasing the amount of relative information improves the classification performance