Forecasting Stock Market Trends by Logistic Regression and Neural Networks: Evidence from KSA Stock Market

Forecasting stock market trends is very vital for investors to take action for the next period for sustainable competition. It is especially important for policy makers to predict actions for development. KSA stock market is evolving rapidly. Due to increasing importance; the aim of this study is to forecast the stock market trends by using logistic model and artificial neural network. Logistic model is a type of probabilistic statistical classification model. It is also used to predict a binary response from a binary predictor, used for predicting the outcome of a categorical dependent variable(i.e., a class label) based on one or more predictor variables (features). Artificial neural networks are models which are used for forecasting because of their capabilities of pattern recognition and machine learning. Both methods are used to forecast the stock prices of upcoming period. The model has used the preprocessed data set of closing value of TASA Index. The data set encompassed the trading days from 5th April, 2007 to 1st January, 2015. Both methods give us estimation with up to 80% accuracy.