Support Vector Machine Classification Model Based on Grey Wolf Optimizer

This paper proposes a support vector machine (SVM) classification model based on the grey wolf optimizer (GWO) to solve high-dimensional nonlinear classification problems in industrial production and daily life. To address the sensitivity of traditional SVM to parameter settings, this study utilizes the global search capability and fast convergence characteristics of the grey wolf optimizer to optimize the key parameters of SVM, including the penalty parameter C and the width parameter g of the radial basis function (RBF). By using the best accuracy rate achieved through five-fold cross-validation as the target function, the precise adjustment of SVM parameters was realized. Experiments using the Italian wine dataset were conducted for verification, and the results showed that the GWO-SVM model achieved a 100% accuracy rate on the test set, proving that the model has high classification accuracy and good generalization ability in handling complex classification problems.