Predicting corporate financial performance in artificial intelligence era: a comprehensive bibliometric study

Purpose This study aims to analyze and identify the applications of artificial intelligence (AI) techniques in predicting corporate financial performance to uncover the main trends and influential contributors, including documents, journals, authors and countries in this research area. Design/methodology/approach This study uses a bibliometric analysis approach incorporating performance analysis and network analysis (science mapping) techniques. By using VOSviewer and Biblioshiny, various analyses are performed, which include encompassing, co-occurrence (co-word), bibliographic coupling, co-citation, thematic evolution, three-field plot and trending topics. Findings The findings identify unique clusters in this area, demonstrating the growth of research topics from fundamental corporate financial performance prediction models to advanced machine learning (ML) applications, giving a road map for future research in this domain. These clusters include ML and deep learning (DL) predictive techniques for corporate financial performance. Furthermore, the findings reveal that random forest, support vector machines, decision trees, logistic regression and artificial neural networks are the most frequent AI methods in corporate financial performance prediction. Overall, this research not only highlights differences in this area but also points to emerging opportunities for deeper exploration and collaboration in underrepresented regions, thereby enriching the global understanding of the role of AI techniques in corporate financial performance prediction. Originality/value This study makes a novel contribution by using science mapping approaches to longitudinally assess the thematic evolution of research in the field of AI-driven financial performance prediction. The distinctive emphasis on the connectivity of themes over time and across geographical regions gives insights that are sometimes overlooked in typical literary studies. This analysis improves understanding of how the discipline has evolved by identifying major patterns and shifts in research focus, particularly during pivotal eras such as the COVID-19 pandemic.