Abstract
The literature on stock forecasting using the innovative technique of Artificial Intelligence (AI) has become overwhelming, making it quite challenging for academics and relevant researchers to gain an elaborative, structured, and organised overview of the relevant information. We fill this gap by contributing and conducting a robust bibliometric review on the application of AI innovations for stock market prediction. More specifically, we conducted a bibliometric review by identifying 241 relevant papers related to stock forecasting using AI by taking a quantitative approach. A quantitative approach uses an examination of linked articles to look at the development of research topics and the structure of existing knowledge. We identified five significant themes based on exploratory factor and hierarchical cluster analyses. We posited that successful AI-based models could aid stock traders, brokers, and investors in better decision-making, a task that had previously been fraught with difficulties. Overall, this paper is aimed at benefiting stock traders, brokers, businesses, investors, government, financial institutions, depositories, and banks. This paper concludes with a future research agenda.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call