Cancer is one of the biggest causes of death in the world. In particular, brain cancer is cancer that occurs in the central nervous system. One of the things that can be done to research brain cancer using machine learning is to detect the types of brain cancer by utilizing data microarrays. These problems are multiclass classification problems. Using the one versus one approach, there will be as many as  two-class problems, where k indicates the number of classes. This study aims to classify the types of brain cancer using support vector machines with the selection of multiple multiclass artificial bee colony based features. In this study the Artificial Bee Colony method will be implemented as a feature selection method and Multiple Multiclass Support Vector Machine (SVM) as a classification method. In the multiclass problem, an Artificial Bee Colony (ABC) training was carried out on each problem in two classes, so that each problem in the two classes had sequencing of each feature. As a classification method, SVM aims to find each class's hyperplane so that first-class data is as close as possible to a hyperplane but as far as possible to other hyperplanes. The outputs of this study are (i) Scientific articles that will be presented at international seminars and (ii) HKI Computer Program classification of brain cancer using the selection of MMABC features and SVM classification. The results of this study are expected to be useful for the community in classifying types of brain cancer more accurately and quickly so that the treatment process can be carried out more specifically and will be able to extend the life expectancy of brain cancer patients.