Abstract
The research aims to construct a predictive model based on the artificial neural network to predict the stock closing price for rationalizing investment decisions. Stock prices are highly volatile, which makes it difficult to predict using traditional methods. Therefore, an applied study has been conducted for two Iraq Stock exchange-listed banks, which are Al-Mansour bank (BMNS) and Investment bank (BIBI), on the basis of daily indices for the period from (2/1/2019) to (28/2/2019). MLP neural network was used in this study to model stock prices using SPSS v26 software. The model was evaluated using a set of metrics, which are MSE, RMSE, MAPE, MAE, and R2. The results proved neural networks' accuracy in predicting stock prices, and thus their dependability in making investment decisions. The researcher recommended conducting more studies in the future.
