Saudi Stock Market Prediction Using Machine Learning and Deep Learning

The research seeks to apply a particular approach to predicting a company's adjusted closing price in hopes of making an advancement in forecasting of the stock price. This research is significant due to its advantages to individuals, corporations, and governments. Approximating a stock's volatility is challenging for traders, and accurate predictions can help investors reduce portfolio risks. Stock prices do not behave in the linear manner. Thus, we suggest the application of artificial intelligence techniques, namely multilayer perceptron (MLP) and long short-term memory (LSTM), to model the changes in Saudi Stock Exchange (Tadawul) index. This research aims at predicting the future of energy, telecommunication, financial, and industrial sectors of the stock exchange. The data was collected from Tadawul for the years 2018–2020 concerning these sectors. The AI algorithms aimed to predict the forthcoming benchmarks for the stock market sectors. The proposed models were tested against actual input data and simulation results, which produced extremely accurate results, demonstrating the effectiveness of the models. In addition, the correlation coefficient (R) of the MLP and LSTM models in predicting the values of Tadawul's four sectors integrated around 0.9950, signifying an exceptional correlation between forecasted and actual results. The forecasts were evaluated using four diverse trials, and between all the algorithms employed, LSTM produced the model's most precise predictions and best-fitting capacity.