Machine learning applications in central banking

Abstract

Central banks are deploying machine learning (ML) across a variety of use cases, reflecting its potential and usefulness in dealing with an increasingly complex environment. The new techniques can help gather more and better information, which is essential for central banks that rely heavily on data. In addition, a key issue is to make sense of the wealth of data available to derive useful analyses on specific economic and financial situations and, in turn, ensure that the insights gained can effectively back the conduct of evidence-based policies. Yet the deployment of the new tools requires further modifications in central banks’ current operational processes and collaboration models, calling for close cooperation between core IT experts, data scientists and business specialists. It also puts a premium on promoting cooperation between central banks through the sharing of national use cases and on drawing relevant lessons from the experiences observed outside the public community.