An Overview on Long Short-Term Memory (LSTM)-Based Prediction Model for Stock Market Volatility

Abstract

Algorithmic trading has revolutionized stock markets, introducing rapid decision-making processes driven by automated systems. Its influence on market dynamics, particularly volatility, has been a subject of intense interest and debate among financial experts and researchers, with a focus on the growing prevalence of algorithmic trading and its potential impact on market stability. This study aims to review related research works that predict the impact of algorithmic trading on stock market volatility using machine learning algorithms. The methodology employed encompassed a comprehensive review of a conceptual framework, empirical review, theoretical review and identifying the gaps within the concept of using machine learning algorithms for the prediction of stock market volatility. The findings of this study provide insight to researchers, investors, traders, and financial institutions such as banks, asset management firms, and hedge funds, for enhancing their risk management practices and also regulators and policymakers to identify models used for predictions.