AN EFFICIENT HYBRID MACHINE LEARNING METHOD FOR TIME SERIES STOCK MARKET FORECASTING

Abstract

Time series forecasting like stock price predicting is one of the most important complications in the financial area with non-stationary and highly-noisy variables, which are affected by many factors. This study applies a hybrid method of Genetic Algorithm (GA) and Artificial Neural Network (ANN) technique to develop a method for predicting stock price and time series. In the GA method,the output values are further fed to a developed ANN algorithm to fix the error on exact point. Our analysis suggests that the GA and ANN can increase the accuracy in less iteration.We analyzed the 200-day main index as well as five of the companies listed on the NASDAQ. By applying the proposed method to the Apple stock dataset, based on a hybrid model of GA and Back Propagation (BP) algorithms; we reach to improvement in SSE and timeimprovement to traditional methods. These results show these performances and the speed and the accuracy of our proposed approach.