<![CDATA[This study examines the intellectual structure and thematic evolution of research on machine learning (ML) in decision support systems (DSS), with particular attention to the financial management domain, through a bibliometric approach spanning 1993 to 2026. Data were retrieved from the Scopus database and analysed using performance analysis and science mapping methods, supported by VOSviewer to identify publication trends, collaboration networks, and co-occurrence patterns. The study reveals an annual growth rate of 13.88% in publications, reflecting sustained and accelerating scholarly interest. Collaboration networks remain fragmented, with China, India, and the United States occupying central positions. Thematic analysis indicates a transition from classical ML methods toward advanced integrations encompassing artificial intelligence, big data, and risk analytics. The findings provide strategic guidance for researchers and practitioners seeking to advance interpretable and ethically grounded ML-based DSS in financial decision-making environments. This study contributes a comprehensive bibliometric mapping of ML in DSS research, identifies persistent intellectual gaps, and proposes a structured agenda for future inquiry integrating explainable AI and cross-disciplinary collaboration.]]>
Copyrights © 2026
