A comparative study of CSO and PSO trained artificial neural network for stock market prediction

Abstract

Stock market prediction is the act of trying to determine the future value of a company stock of other financial Instrument traded on a financial exchange. This paper presents a comparison between, PSO and CSO trained Neural Network to predict the stock rates by preparing data which acts as input. The data is prepared in such a way that the external factors like traditional issues can be mitigated. Earlier Neural Network was trained using Back Propagation algorithm but it converges to local optima and cannot be applied to discrete functions. Sow we have chosen PSO and CSO optimization algorithm to train the Neural Network. The results show that training neural network with such data gives a better performance. © 2011 Springer-Verlag Berlin Heidelberg.