Application of Particle Swarm Optimization Algorithm in Stock Markets

R. Simutis and J. Nenortaite (Lithuania)

Keywords

Stock Markets, Artificial Intelligence, Swarm Intelligence.

Abstract

The objective of this paper is to introduce the decision mak ing model for stock markets. By introducing this model we attempt to make onestep forward decision for selling or buying stocks. The proposed model is based on the study of historic data and the application of Neural Networks and Particle Swarm Optimization (PSO) algorithm. In brief, the proposed model draws from the analysis of historical stock prices fluctuations, which is made by the application of "single layer" neural networks. Further, the application of PSO algorithm follows. The core idea of this algorithm application is to select the "global best" neural networks for the future investment decisions and to adapt the weights of other networks towards the weights of the best network. The experimental investigation results presented in this pa per show the potential of PSO algorithm applications for the decision making in the stock markets.

Important Links:



Go Back