Article citationsMore>>

Moradi A., M., Sadrossadat, S. A., & Derhami, V. (2021). Long Short-Term Memory Neural Networks for Modeling Nonlinear Electronic Components. IEEE Transactions on Components, Packaging and Manufacturing Technology, 11, 840-847.
https://doi.org/10.1109/tcpmt.2021.3071351

has been cited by the following article:

• TITLE: Prediction of the Price of Advanced Global Stock Markets Using Machine Learning: Comparative Analysis

  AUTHORS: Mohanned Hindi Alharbi

  KEYWORDS: Global Stock Markets, Forecast, Long Short-Term Memory (LSTM), Predictive Accuracy, Investment Decisions, Financial Analysts

  JOURNAL NAME: Journal of Financial Risk Management, Vol.13 No.4, December 12, 2024

  ABSTRACT: This paper seeks to forecast the daily closing prices of advanced global stock markets by employing machine learning techniques. It includes a comparative analysis of four major indices: TASI, the S&P 500, FTSE100, and DAX Price Index. Historical data from these indices were used to train various machine learning models, such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid Model between LSTM and GRU. The models were assessed by considering their predictive accuracy, mean squared error (MSE), and computational efficiency. Furthermore, it emphasizes the power of machine learning in forecasting stock market daily closing prices and highlights the significance of choosing suitable models for varying market conditions. This analysis offers valuable insights into the evolution of more reliable forecasting tools, which can assist in risk management and strategic investment decisions.