Data quality measures based on granular computing for multi-label classification

Abstract

Rough set theory is a granular computing formalism that allows analyzing a given dataset through well-defined measures. Some of these measures aim to characterize datasets used to discover knowledge, mostly in traditional classification problems. Measuring the data quality is pivotal to estimate beforehand the problem’s difficulty since a classification model’s accuracy heavily depends on the data quality. However, to the best of our knowledge, there are no measures devoted to analyzing the quality of multi-label datasets. In this paper, we propose six data quality measures for multi-label problems, which are based on different granular approaches. Some of these measures redefine the decision class concept, while others redefine the consistency concept. Moreover, we study the impact of the similarity threshold parameters and the distance functions on the behavior of these measures. The numerical simulations show a statistical correlation between the measures that redefine the consistency concept and the performance of the ML-kNN classifier.