Entropy-based intuitionistic fuzzy least squares twin support vector machine for class imbalance learning

Purpose Support vector machine (SVM) and twin support vector machine (TSVM) are plane-based classifiers that perform well on balanced datasets. However, their performance significantly degrades on imbalanced datasets due to their limited ability to model class proportions, noise, and outliers. To address this issue, this paper proposes an entropy-based intuitionistic fuzzy least squares twin support vector machine for class imbalance learning (EIFLSTSVM-CIL). Design/methodology/approach This study proposes a class imbalance learning method that embeds entropy-driven intuitionistic fuzzy modeling into the least squares twin support vector machine framework. Specifically, each sample is assigned the degrees of membership and nonmembership by jointly considering its spatial distribution in the feature space and the uncertainty of its class association measured by information entropy. In addition, sample weights are adjusted based on the global imbalance ratio, which enhances the penalization of majority class outliers and noisy instances. The proposed method is evaluated on 21 synthetic datasets and 35 real-world benchmark datasets with varying imbalance ratios. Findings Experimental results on 21 synthetic datasets and 35 real-world datasets demonstrate that EIFLSTSVM-CIL exhibits superior robustness and generalization performance in imbalanced scenarios, showing a significant advantage over classical models. Originality/value This study enhances the twin least squares SVM by jointly incorporating entropy-based intuitionistic fuzzy modeling and class-imbalance weighting. The proposed approach integrates both aspects in a unified framework, improving robustness and generalization on imbalanced data.