A Hybrid Approach for Integrating Genetic Algorithms with SVM for Classification and Modelling Higher Education Data

Higher education institutions are hub of research and future development acting in a competitive scenario, with the basic goal to generate, gather and share knowledge. In this research work my objective is to explore data mining technique like classification, clustering on higher education data, my objective is to integrate genetic algorithm (GA) and support vector machines algorithm (SMO), for integration of two classifiers we use ensemble stacking, which is a fusion of classifiers. We present a generalize and powerful hybrid methodology of spectral clustering which originally operates on SMO and genetic algorithm classifiers, and further develop algorithms for classification on the basis of minimum attribute selecting and normalisation of dataset. It could be concluded that the proposed GA-SMO classifier approach improves the classification accuracy and gives the better results, than other methods.