Predicting Firm Performance with Data Mining: A Systematic Review and Bibliometric Analysis

Abstract

Firm performance is a critical driver of economic growth and investor confidence, impacting a wide range of stakeholders, including creditors, employees, managers, and governments. This study systematically examines the literature on predicting firms' performance using Data Mining (DM) techniques by combining a Systematic Literature Review (SLR) with bibliometric analysis. The review covers articles published between 2017 and 2024 across six major publishers. It identifies six key research themes: stock price prediction, customer-centric research, financial distress prediction, textual analysis, business cycle analysis, and ensemble boosting methods. Findings reveal that Saudi Arabia and the United Arab Emirates lead contributions within the Gulf Cooperation Council (GCC), while other GCC countries remain underrepresented, highlighting a regional research gap. The review also uncovers limited use of GCC datasets and underexplored dependent variables, such as profitability. A key limitation is reliance on the Web of Science database, which is partially mitigated by including 9 additional articles identified through website and citation searches. Overall, this study provides an updated, structured overview of DM applications in predicting firm performance, offers practical insights for researchers and business professionals, and identifies opportunities for future research in the GCC context.