Financial Risk Assessment using Machine Learning : A Bibliometric Analysis

Faced with unstable financial markets, financial institutions and fund managers are expected to adopt a new paradigm by integrating technological innovations, notably machine learning, to measure, assess and manage financial risks. This article focuses on a bibliometric analysis of research on financial risk assessment using machine learning. From a total of 1,100 documents, only 633 were selected from the Scopus database according to specific selection criteria. These selected sources were subjected to bibliometric analysis using VOSviewer software. The aim is to consolidate existing research over the last decade (2014-2023), while analyzing these trends, identifying the most influential authors, the temporal and geographical distribution of publications, as well as the most productive affiliations in this field. The results indicate a notable increase in publications in this field, mainly over the 2014-2023 period. Some authors stand out in the discipline either through a significant number of citations or a high volume of publications. These include Ribeiro, B. (295 papers, 3593 citations), Chen, N. (984 papers, 61 citations), Moscato, V. (226 papers, 3400 citations).