ویراساینس.
سند علمی

A study on cost behaviors of binary classification measures in class-imbalanced problems

Bao-Gang Hu, Weiming Dong

چکیده

This work investigates into cost behaviors of binary classification measures in a background of class-imbalanced problems. Twelve performance measures are studied, such as F measure, G-means in terms of accuracy rates, and of recall and precision, balance error rate (BER), Matthews correlation coefficient (MCC), Kappa coefficient (κ), etc. A new perspective is presented for those measures by revealing their cost functions with respect to the class imbalance ratio. Basically, they are described by four types of cost functions. The functions provides a theoretical understanding why some measures are suitable for dealing with class-imbalanced problems. Based on their cost functions, we are able to conclude that G-means of accuracy rates and BER are suitable measures because they show “proper” cost behaviors in terms of “a misclassification from a small class will cause a greater cost than that from a large class”. On the contrary, F1 measure, G-means of recall and precision, MCC and κ measures do not produce such behaviors so that they are unsuitable to serve our goal in dealing with the problems properly.

اسناد مشابه

  • A bias correction function for classification performance assessment in two-class imbalanced problems

    سند علمی۲۰۱۴Knowl.-Based Syst.Vicente García, Ramón Alberto Mollineda, José Salvador Sánchez

    This paper introduces a framework that allows to mitigate the impact of class imbalance on most scalar performance measures when used to evaluate the behavior of classifiers. Formally, a correction function is defined with the aim of highlighting those classification results that

  • Using Self-organizing Maps for Binary Classification with Highly Imbalanced Datasets

    سند علمی۲۰۱۴VINICIUS ALMENDRA

    Highly imbalanced datasets occur in domains like fraud detection, fraud prediction, and clinical diagnosis of rare diseases, among others. These datasets are characterized by the existence of a prevalent class (e.g. legitimate sellers) while the other is relatively rare (e.g. fra

  • Support Vector Machines Classification on Class Imbalanced Data: A Case Study with Real Medical Data

    سند علمی۲۰۱۵Krystallenia Drosou, Stelios Georgiou, Christos Koukouvinos, Stella Stylianou

    support vector machines (SVMs) constitute one of the most popular and powerful classification methods. However, SVMs can be limited in their performance on highly imbalanced datasets. A classifier which has been trained on an imbalanced dataset can produce a biased model towards

  • Instance Selection for Class Imbalanced Problems by Means of Selecting Instances More than Once

    سند علمی۲۰۱۱CAEPIAJavier Pérez-Rodríguez, Aida de Haro-García, Nicolás García-Pedrajas

    Although many more complex learning algorithms exist, knearest neighbor (k-NN) is still one of the most successful classifiers in real-world applications. One of the ways of scaling up the k-nearest neighbors classifier to deal with huge datasets is instance selection. Due to the

  • Population structure-learned classifier for high-dimension low-sample-size class-imbalanced problem

    مقاله‌ی دسترسی آزاد۲۰۲۲Engineering Applications of Artificial Intelligence['Li-Ran Shen', 'Meng Joo Er', 'Qing-Bo Yin', '']

    The classification on high-dimension low-sample-size data (HDLSS) is a challenging problem and it common to have class-imbalanced in most application fields. We term this as Imbalanced HDLSS (IHDLSS). Recent theoretical results reveal that the criterion tolerance similarity are c

  • A combined SMOTE and PSO based RBF classifier for two-class imbalanced problems

    سند علمی۲۰۱۱NeurocomputingMing Gao, Xia Hong, Sheng Chen, Christopher J. Harris

    This contribution proposes a powerful technique for two-class imbalanced classification problems by combining the synthetic minority over-sampling technique (SMOTE) and the particle swarm optimisation (PSO) aided radial basis function (RBF) classifier. In order to enhance the sig