Fuzzy twin SVM based on Hilbert–Schmidt independence criterion and information entropy for imbalanced learning

Purpose Imbalanced learning presents a significant challenge in the field of machine learning. Although traditional support vector machine (SVM) demonstrate relatively robust performance when handling imbalanced datasets, they assign equal learning contributions to all samples, which can lead to decision boundaries that are biased toward the majority class, especially in the presence of outliers or noise. To address this issue, this paper proposes a fuzzy SVM model based on the Hilbert–Schmidt independence criterion (HSIC) heuristic strategy and information entropy (HEFTSVM) for imbalanced learning. Design/methodology/approach This study introduces an effective fuzzy membership allocation strategy combining HSIC heuristic strategies and information entropy. The fuzzy membership function leverages structural information derived from both the input and feature spaces. Specifically, entropy assesses membership within the input space, whereas HSIC evaluates it in the feature space. The final fuzzy membership function is derived by multiplying the memberships from both spaces. This approach is integrated with the twin support vector machine (TSVM) algorithm to create the HEFTSVM algorithm. We evaluated the model’s effectiveness through comparative experiments on 39 datasets with varying imbalance levels. Findings Experimental results validate the effectiveness of HEFTSVM in addressing class imbalance classification problems, achieving an average geometric mean (GM) of 86.71% on low-imbalance datasets and 82.13% on high-imbalance datasets. These findings demonstrate that HEFTSVM exhibits better robustness and generalization performance than existing learning models. Originality/value This study proposes a fuzzy membership degree allocation strategy based on HSIC heuristic and information entropy, effectively addressing the class imbalance issue, mitigating the sensitivity of TSVM to noise and introducing the noise-robust HEFTSVM model.