The use of support vector machine and Naive Bayes algorithms and its combination with risk measure and fuzzy theory in the selection of stock portfolio

The purpose of the current research is to create an optimal portfolio using machine learning algorithms and fuzzy theory, which has a better return than the average return of the market (total index of the stock exchange).

In this article, the stocks of the selected companies are classified in the first stage using the two introduced algorithms. In the next step, stocks that entered the positive class are predicted for the next trading day with the help of random forest algorithm. For each company, three predictions are made, which are the inputs of fuzzy method optimization. Optimization is done with the aim of minimizing the risk with risk measures of value at risk and value at conditional risk. Shares information is five years old (daily) and its time period is from the beginning of 2017 to the end of 2021.

In the end, each of the algorithms and the risk measure used were measured and compared with the actual market return. Based on the obtained results, the CVAR risk measure has a better capability and result than the VAR risk measure, and the support vector machine algorithm has also achieved a better performance in choosing the investment portfolio.

Originality/ value: 

This research is optimized in the form of a capital sample by integrating machine learning methods and risk measures. Adding VaR and CVaR risk metrics enhances the decision-making process regarding risk reduction. Forecasting with the help of random forest and using an approach based on fuzzy theory for risk and value analysis gives the research an innovative perspective in portfolio formation. The findings provide investors and researchers with valuable insights in their search for better investment strategies.