Prediction of Stock Market Indices using Hybrid Genetic Algorithm/ Particle Swarm Optimization with Perturbation Term

Stock market indices prediction is one of the most important issues in the financial field. Although many prediction models have been developed during the last decade, they suffer a poor performance because indices movement is highly non stationary and volatile dynamic process. As improving the prediction accuracy becomes an important issue, we propose a new hybrid genetic Algorithm / Particle Swarm Optimization (GA/ PSO) model with perturbation term inspired by the passive congregation biological mechanism to overcome the problem of local search restriction in standard hybrid (GA/ PSO) models. This perturbation term is based on the cooperation between different particles in determining new positions rather than depending on the particles selfish thinking which enables all particles to perform the global search in the whole search space to find new regions with better performance. Experiment study carried out on the most famous stock market indices in both long term and short term prediction shows significantly the influence of the perturbation term in improving the performance accuracy compared to standard hybrid (GA/ PSO) models.