A REVIEW ON PREDICTION OF STOCK MARKET USING MACHINE LEARNING

With the introduction of technical wonders such as worldwide digitalization, stock market forecasting has entered a technologically enhanced era, reviving the traditional trading methodology. Stock trading has become a center of investment for many financial investors as market capitalization continues to rise. Many analysts and researchers have created tools and approaches to forecast stock price fluctuations and assist investors in making informed decisions. Researchers can use advanced trading algorithms to forecast the market using non-traditional textual data from social media networks. The use of modern machine learning techniques like text data analytics and ensemble algorithms has substantially improved prediction accuracy. Meanwhile, due to its dynamic, irregular nature, stock market analysis and prediction remain one of the most difficult study disciplines. Based on the deployment of a generic framework, this paper illustrates the systematics of machine learning-based systems for stock market prediction. Findings from the previous decade (2011–2021) were evaluated using online digital libraries and databases such as the ACM digital library and Scopus. In addition, a thorough comparison study was performed to determine the direction of significance. The study will aid emerging researchers in understanding the fundamentals and accomplishments of this new field, allowing them to pursue additional research in promising paths.