Forecasting common stock returns using Artificial neural networks models: An application Study on commercial banks in Iraqi Stock Exchange for the period (2006-2023)

Abstract

The article aims to improve the investment decision of the investor in Common stock in the Iraq Stock Exchange through the use of time series models and neural networks to obtain accurate prediction values ​​that rationalize the investment decision, Perhaps neural network models were and still represent an intellectual debate about their validity and preference in predicting Common

stock returns, Therefore, this Article came to find out this controversy and try to solve it by testing the above models in the light of the data obtained for the Article sample represented by the banks listed in the Iraq Stock Exchange and by (10) banks for the period from (30/6/2006) to (31/1/2023), by (198) months (watching), And using many financial, statistical and mathematical methods, The Article reached a number of conclusions, Perhaps the most important of them is the superiority of multilayer perceptron network models in reaching accurate prediction values ​​at the level of the Article sample banks, The Article came out with a number of recommendations, Perhaps the most important of them is the need to adopt multi-layered perceptron network models in predicting the returns of common stocks of the article sample banks