Applications of Deep Learning Techniques in Stock Market Forecasting: A Bibliometric Analysis

The increasing adoption of deep learning techniques has ignited considerable interest among portfolio managers, investors, and speculators. Using bibliometric analysis, this study examines 392 journal articles procured from the Scopus database, which have explicitly applied deep learning methods for stock market data forecasting. The study highlights the key publications, influential journals, prominent authors, prestigious institutions, and notable nations that have contributed to the field's research through this thorough investigation. This study conducts keyword co-occurrence analysis to identify potential clustering of topics. The study also presents a research agenda for the future and emphasises the significance of hybrid models, real-time forecasting capabilities, and enhanced interpretability. This research offers useful insights into the application of deep learning techniques in equity market forecasting, catering to the interests and demands of stakeholders in this fascinating field by elucidating the existing literature and offering a path for future investigations.