Since analysis of time series is so hard to do, a support vector machine can be more proper for the purpose of forecasting in field of stock market. The support vector machine (SVM) can explore suitable knowledge from so vague data, which usually is necessary to interpret the financial data. But single SVM cannot achieve accurate results. Subsequently, in this paper a combinational intelligent strategy is presented. The proposed strategy consists of genetic algorithm (GA) and SVM for the purpose of stock market forecasting. The genetic algorithm is useful to choose the most informative input indicators from among all the technical indicators. A variety of indicators from the technical analysis field of study are used as input features. Based on obtained results, the hybrid GA-SVM system performs better than Neural Network system.
Key words: Stock price forecast, genetic algorithm, support vector machine.
SVM, Support vector machine; GA, genetic algorithm; NN, neural networks; EMH, efficient market hypothesis; AI, artificial intelligence; SXGE, Swedish stock index; HR, hit rate; RP, realized potential; PSO, particle swarm optimization; RBF,radial basis function.
Copyright © 2023 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0