TECHNIQUES FOR TIME SERIES PREDICTION: - A REVIEW

Abstract

This paper shows a recent literature survey on stock market prediction with the help of machine learning techniques. Neural network based models identified as the technique which is used by most of the researcher working on currency exchange rate prediction. Neural networks like artificial neural network(ANN) ,functional link artificial neural network (FLANN)radial basis function network(RBFN), wavelets neural network (WNN) ,Psi Sigma neural networks etc are ensemble with many other learning techniques such as least mean square(LMS) ,genetic algorithm(GA), particle swarm optimization (PSO)etc to improve the accuracy and the efficiency. Given currency exchange market model uncertainty, soft computing techniques are viable candidates to capture stock market nonlinear relations returning significant forecasting results.