In this study, we presented a feature extraction approach that addresses the difficulties arising from high dimensionality and large datasets in classification tasks. Our method combined differential evolution algorithmwith Support Vector Machines (SVM). The experimental results demonstrated that SVM struggled when applied to large datasets. The proposed approach aimed to identify the most relevant features from the dataset, ultimately improving the accuracy of classification tasks. By reducing the data's dimensionality, we achieved storage efficiency and enhanced the classification process. This research provides valuable insights into the effectiveness of DE algorithm in overcoming challenges related to high-dimensional and large datasets, making a significant contribution to the field of feature selection and classification. Future research can explore the application of these approaches to other datasets and explore ways to further improve the efficiency and effectiveness of classification tasks.