Predicting Saudi Stock Market Index by Using Multivariate Time Series Based on Deep Learning

Abstract

Time-series (TS) predictions use historical data to forecast future values. Various industries, including stock market trading, power load forecasting, medical monitoring, and intrusion detection, frequently rely on this method. The prediction of stock-market prices is significantly influenced by multiple variables, such as the performance of other markets and the economic situation of a country. This study focuses on predicting the indices of the stock market of the Kingdom of Saudi Arabia (KSA) using various variables, including opening, lowest, highest, and closing prices. Successfully achieving investment goals depends on selecting the right stocks to buy, sell, or hold. The output of this project is the projected closing prices over the next seven days, which aids investors in making informed decisions. Exponential smoothing (ES) was employed in this study to eliminate noise from the input data. This study utilized exponential smoothing (ES) to eliminate noise from data obtained from the Saudi Stock Exchange, also known as Tadawul. Subsequently, a sliding-window method with five steps was applied to transform the task of time series forecasting into a supervised learning problem. Finally, a multivariate long short-term memory (LSTM) deep-learning (DL) algorithm was employed to predict stock market prices. The proposed multivariate LSTMDL model achieved prediction rates of 97.49% and 92.19% for the univariate model, demonstrating its effectiveness in stock market price forecasting. These results also highlight the accuracy of DL and the utilization of multiple information sources in stock-market prediction.

DESTformer: A Transformer Based on Explicit Seasonal–Trend Decomposition for Long-Term Series Forecasting

“…As a standard method for time series analysis, time series decomposition [22] decomposes time series into several different levels of representation, each of which can represent a predictable potential category and has mainly been used to explore historical changes over time. For prediction tasks, decomposition was usually used as a preprocessing step for historical sequences before predicting future sequences [23][24][25], such as trend-seasonal decomposition in Prophet [26], basis expansion in N-BEATS [27], and matrix decomposition in DeepGLO [28]. However, such a reprocessing operation was limited by the simple decomposition of historical sequences and ignored the hierarchical interaction between underlying patterns of long-term future sequences.…”