A prediction-based portfolio optimization model using support vector regression

The purpose of portfolio optimization is to select an optimal combination of financial assets, which should be a guide for investors to achieve the highest returns against the lowest possible risk. On the other hand, one of the key factors in portfolio optimization decisions is related to predict the stock prices. To do this, classical nonlinear mathematical and intelligent models such as regression are commonly used. In the present study, a nonlinear model of support vector regression with multiple outputs is applied to reduce the prediction errors. To show the effectiveness of the proposed model, the data of S & P500 index companies in the period 12/09/2016 to 02/08/2021 is used. The results show that the selection of a portfolio based on prediction using multiple vector backup regression due to considering the relationships between outputs simultaneously in terms of Sharp criteria has a better performance than the selection of portfolio based on prediction using regression method.