A preliminary study of ordinal metrics to guide a multi-objective evolutionary algorithm

• Published in: 2011 11th International Conference on Intelligent Systems Design and Applications pp. 1176 - 1181
• Main Authors: Cruz-Ramirez, M., Hervas-Martinez, C., Sanchez-Monedero, J., Gutierrez, P. A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2011
• Subjects: Analytical models; Correlation; Evolutionary computation; Intelligent systems; mean absolute error; Measurement uncertainty; multi-objective evolutionary algorithm; ordinal measures; Training
• ISSN: 2164-7143
• DOI: 10.1109/ISDA.2011.6121818

There are many metrics available to measure the goodness of a classifier when working with ordinal datasets. These measures are divided into product-moment and association metrics. In this paper, the behavior of several metrics is studied in different situations. In addition, two new measures associated with an ordinal classifier are defined: the maximum and the minimum mean absolute error of all the classes. From the results of this comparison, a pair of metrics is selected (one associated to the overall error and another one to the error of the class with lowest level of classification) to guide the evolution of a multi-objective evolutionary algorithm, obtaining good results in generalization on ordinal datasets.