Comparison of Machine Learning Algorithms for Classification Problems

Machine learning algorithms become wide tools that are used for classification and clustering of data. Several algorithms were proposed and implemented for different applications in multi-disciplinary areas. However, diversity of these algorithms makes the selection of effective algorithm difficult for specific application. Thus, comparison of benchmark algorithms is required. This paper presents preliminary results of the comparison of three different types of machine learning algorithms; Backpropagation Neural Network, Radial Basis Function Neural Network and Support Vector Machine using several numerical datasets for classification problems. Comparison is performed by considering the performance of these algorithms using obtained accuracy rates. The results show that Radial Basis Function Neural Network is superior to other considered algorithms for classification of numerical data.