A Particle Swarm Optimization Approach in the Construction of Decision-making Model

The paper introduces an intelligent decision-making model which is based on the application of artificial neural networks (ANN) and swarm intelligence technologies. The proposed model is used to generate one-step forward investment decisions for stock markets. The ANNs are used to make the analysis of historical daily stock returns and to calculate one day forward possible profit, which could be get while following the model proposed decisions, concerning the purchase of the stocks. Subsequently the Particle Swarm Optimization (PSO) algorithm is applied in order to select the "global best" ANNs for the future investment decisions and to adapt the weights of other networks towards the weights of the best network. While working with the proposed model we have focused on the problem of gathering the data and making analysis of different models as it was very time consuming. In order to improve data gathering process and analysis tools we developed a decision-making system. The paper introduces a trading system for stock markets, which is designed as a framework for development and evaluation of intelligent decision-making models. The paper introduces experimental investigations on decision-making model performance when the decision making and training of ANN is made using a group of particles.