Oscar Garnica

1 month ago | onlinelibrary.wiley.com | Alberto Gutiérrez-Gallego |Oscar Garnica |Daniel Parra |J. Manuel Velasco

1 Introduction In the last decade, machine learning applications have increased substantially due to technological advances, data availability and algorithm improvements, making the refinement of these models challenging. While conventional metrics like accuracy, recall or F-score are commonly employed to assess models, they frequently offer a limited view of the performance of the models for the full scope of the configuration of the hyperparameters.