Machine Learning Applied to Banking Supervision a Literature Review

Machine learning (ML) has revolutionised data analysis over the past decade. Like innumerous other industries heavily reliant on accurate information, banking supervision stands to benefit greatly from this technological advance. The objective of review is provide a comprehensive walk-through how most common ML techniques have been applied risk assessment in banking, focusing supervisory perspective. We searched Google Scholar, Springer Link, and ScienceDirect databases for articles including search terms “machine learning” (“bank” or “banking” “supervision”). No language, date, Journal filter was applied. Papers were then screened selected according their relevance. final article base consisted 41 papers 2 book chapters, 53% which published top quartile journals field. Results are presented timeline publication date categorised by time slots. Credit stress testing highlighted topics as well perspectives, with some references application surveys. relevant encompass k-nearest neighbours (KNN), support vector machines (SVM), tree-based models, ensembles, boosting techniques, artificial neural networks (ANN). Recent trends include developing early warning systems (EWS) bankruptcy refining testing. One limitation study paucity contributions using data, justifies need additional investigation However, there increasing evidence that can enhance decision making industry.