General Performance Score for classification problems

Abstract

Several performance metrics are currently available to evaluate the performance of Machine Learning (ML) models in classifcation problems. ML models are usually assessed using a single measure because it facilitates the comparison between several models. However, there is no silver bullet since each performance metric emphasizes a diferent aspect of the classifcation. Thus, the choice depends on the particular requirements and characteristics of the problem. An additional problem arises in multi-class classifcation problems, since most of the well-known metrics are only directly applicable to binary classifcation problems. In this paper, we propose the General Performance Score (GPS), a methodological approach to build performance metrics for binary and multi-class classifcation problems. The basic idea behind GPS is to combine a set of individual metrics, penalising low values in any of them. Thus, users can combine several performance metrics that are relevant in the particular problem based on their preferences obtaining a conservative combination. Diferent GPS-based performance metrics are compared with alternatives in classifcation problems using real and simulated datasets. The metrics built using the proposed method improve the stability and explainability of the usual performance metrics. Finally, the GPS brings benefts in both new research lines and practical usage, where performance metrics tailored for each particular problem are considered.