Cancer is one of the most famous diseases in recent years. Cancer has various classifications, which are difficult to detect in patients. Most patients are diagnosed with cancer after being at an advanced stage. To analyze the disease and diagnose cancer in patient, we need gene expression data. Gene expression data contain so many genes, even thousands of genes, but not all of those genes contain information necessary to detect cancer for its classification. Machine learning can choose the important genes for the classification to reduce running time, cost, and increase classification accuracy. In this paper we use Stochastic SVM and Fuzzy Kernel Robust C-Means (FRKCM). Then we will compare the accuracy of the methods in breast cancer classification. Stochastic SVM achieves a high prediction accuracy by learning the optimal hyperplane from the training set, which greatly simplifies the classification and regression problems. Fuzzy Kernel Robust C-Means (FKRCM) will define the membership function, set specific data called prototype and use the learning rate on each iteration. Based on the experiment, we get 90.43 % accuracy for the Stochastic SVM and 95.65 % accuracy for Fuzzy Kernel Robust C-Means.