Exploring Global Scholarly Contributions to AI-Driven Stock Prediction through Analytics: A Bibliometric Evaluation

Machine Learning, Bibliometrics, Stock market, Artificial Intelligence, Science mapping, knowledge management

The financial market plays a pivotal role in global economy and is a domineering field of research. It not only provides corporates a way to raise capital to fund their operations and expansion plans but additionally, provides investors with an opportunity to earn a return on their investments and grow their wealth over time. Although the massive usage of machine learning techniques in stock market field is up trending, there has been little focus on developing a framework that synthesizes the primary trends and research on the topic. This study is one of the attempts to thoroughly investigate the published literatures in few decades and focuses on addressing this gap by conducting further analysis of complementary bibliographic sources, evaluating 834 reputable bibliometric studies published in the Scopus database. A total of 2,037 authors contributed to publications, with 58 authors writing 68 documentsindividually and 19.78% of these authors have engaged in international collaborations. The average number of citations per document is 24.02. The leading nations with greatest number of publicationsare CHINA, INDIA and US ,i.e., with 238,210 and 82 articles respectively. The prominent journal is ‘Expert Systems with Applications’ (with 57 articles) and the most productive authors areLI X and WANG X (with 14 articles each) inthe Scopus database. This research reveals that as subset of AI (Artificial Intelligence), the ML (Machine Learning) and the DL(Deep Learning) application in stock market is evolving and expanding. This paper enhances the existing literature by offering a thorough overview of the articles that focuses on application of AI and ML in stock market prediction.