Integration of Principal Component Analysis and Recurrent Neural Network to Forecast the Stock Price of Casablanca Stock Exchange

Time series analysis is an important field that, recently, captivate researchers attention. It represents a lot of real problems, one of them is the prediction of the stock prices. As known, the recurrent neural network (RNN) is the most used model for the prediction problem, since it gives good results for time series forecasting. This paper aims to forecast the stock price of Total Maroc for 29 days from Casablanca Stock Exchange, using principal component analysis (PCA) in order to reduce the number of features from eight to six. The use of dimensionality reduction enhances the accuracy of the recurrent neural network model and gives a good prediction for the stock price. (C) 2019 The Authors. Published by Elsevier B.V.