This study aims to systematically examine the academic publications in the fields of portfolio and machine learning and to analyze the emerging literature using bibliometric methods. Publications obtained from the Web of Science (WoS) database were searched using relevant keywords, and the resulting data were evaluated in detail in terms of publication trends by year, contributing institutions, countries, highly cited studies, and frequently used keywords.

The findings suggest that the application of machine learning techniques in portfolio management has experienced rapid growth, particularly in recent years. Algorithms such as artificial neural networks, random forests, and support vector machines are frequently used in tasks involving prediction, classification, and optimization problems.

Through bibliometric analysis, the current state of the field has been comprehensively revealed. Additionally, the analysis highlights thematic gaps and suggests potential directions for future research. In this respect, the study serves as a valuable reference for both researchers and practitioners.