University of Guilan Computational Sciences and Engineering 2783-2503 4 2 2025 09 06 A New Insight on the Model of Support Vector Machine 297 308 9037 10.22124/cse.2025.31583.1118 EN Afsaneh Pourmoezi Department of Applied Mathematics, University of Mazandaran, Babolsar, Iran Mostafa Eslami Department of Applied Mathematics, University of Mazandaran, Babolsar, Iran Ali Tavakoli Department of Applied Mathematics, University of Mazandaran, Babolsar, Iran Journal Article 2025 07 03 Support Vector Machine (SVM) is a powerful classification algorithm that separates samples by finding an optimal decision boundary. Its performance can degrade when feature variances differ across classes, potentially leading to suboptimal decision boundaries. A variance-weighted framework is proposed that reduces the influence of high-variance features while enhancing the impact of low-variance features, resulting in more accurate and robust decision boundaries. The method is applicable in both linear and nonlinear settings. Evaluation on synthetic datasets and real-world datasets, including Breast cancer and <em>a9a</em>, using cross-validation demonstrates that the variance-weighted SVM achieves higher accuracy and F1-score compared to soft SVM and LDM, particularly in scenarios with significant variance differences between classes. https://cse.guilan.ac.ir/article_9037_d305209df9180d00c147fe174517f0eb.pdf