Machine Learning Techniques in Predicting Firms' Performance: A Bibliometric Analysis

Predicting firms' performance has long been challenging for stakeholders, such as investors, shareholders, creditors, and government entities. With the exponential growth of financial data, Machine Learning (ML) techniques have emerged as a vital area of research in predicting firms' performances. This study aims to investigate recent scholarly articles that have employed ML techniques to predict the performance of firms. A bibliometric analysis has been conducted on the Web of Science (WoS) database spanning 2017 to March 2024 to explore the productivity of research contributors and the impact of their publications. This analysis aims to identify key themes, topics, and trends in the field. After the study, six main themes were discovered in the literature: stock price, customer-centric, bankruptcy prediction, businesscycle assessment, textual analysis, and ensemble-boosting techniques. The study is essential as it provides a better understanding of the existing research on ML techniques for firms' performance prediction. Researchers can use it to pinpoint gaps in knowledge and pave the way for further research in this area.