Performance comparison of artificial neural network (ANN) and support vector machines (SVM) models for the stock selection problem: An application on the Istanbul Stock Exchange (ISE) - 30 index in Turkey

Abstract

Support vector machines (SVM) and artificial neural networks (ANN) are machine learning methods that find a wide range of applications both in the field of engineering and social sciences. Recently, studies especially in the field of finance for the classification and estimation make it necessary to use these methods often in this area. In this study, different SVM and ANN models for the problem of stocks selection which provide maximum returns have been applied on different combinations of data sets which obtained from the balance sheets, stocks prices and the results of a comparative analysis has been presented. The findings show that SVM and ANN models including financial ratios give meaningful performance results for the stock selection. Key words: Support vector machines, artificial neural networks, stock selection, financial ratios, feature selection.