Forecasting Stock Market with Support Vector Regression and Butterfly Optimization Algorithm

The problem of forecasting stock price movements, due to market's uncertainty from incoming news, nonlinear financial instruments and behavioral and emotional biases is a challenging task facing academics and practitioners in the field; perhaps by far more complex than predicting the course of a comet by a physicist. In the past, many models have been proposed to face this problem including Support vector regression (SVR) as the extended routine designed from Support Vector Machines (SVM). Originally introduced by Vapnik for classification problems, SVM was redesigned to solve regression problems in the SVR framework. Nevertheless, SVM can solve small-sample, nonlinear and high dimension problems by using the structural risk minimization principle instead of the empirical risk principle, which could theoretically guarantee to achieve the global optimum [9]. Although SVR experimental results have shown great performance compared to other nonlinear methods [39, 40], its performance mainly depends on the choice of parameters.