Comparative study between Differential Evolution and Particle Swarm Optimization algorithms in training of feed-forward neural network for stock price prediction

This paper presents a comparison between two stochastic, population based and real-valued algorithms. These algorithms are namely Differential Evolution (DE) and Particle Swarm Optimization (PSO). These algorithms are used in the training of feed-forward neural network to be used in the prediction of the daily stock market prices. Stock market prediction is the act of trying to determine the future value of a company stock or other financial instrument traded on a financial exchange. The successful prediction of a stock´s future price could yield significant profit. The feasibility, effectiveness and generic nature of both DE and PSO algorithms are demonstrated. These algorithms are proposed to solve the problems of traditional training techniques like local minima and overfitting. Comparisons were made between the two approaches in terms of the prediction accuracy, convergence speed and generalization ability. The proposed model is based on the study of historical data, technical indicators and the application of Neural Networks trained with DE and PSO algorithms. The simulation results presented in this paper show the potential of both two algorithms in solving the problems of traditional training techniques. DE algorithm is better than PSO algorithm in prediction accuracy, convergence speed and handling fluctuated stock time series.