Unsupervised Machine Learning in Risk Management
Machine learning has come to play an important role in the banking and finance industry thanks to unprecedented growth in the availability of computing power, data storage, and algorithms. As many banks are increasingly implementing and employing such technologies, machine learning has the potential to change many traditional banking processes.
In order to properly assess and keep up with these developments, banking professionals need a basic understanding of the underlying machine learning algorithms.
Objective
In this Master Class, we discuss some of the most important machine learning task. Topics include an introduction to the relevant machine learning algorithms and performance metrics, and to their concrete application in the context of unsupervised fraud detection. Unsupervised learning algorithms can detect patterns in high-dimensional unstructured data, which exceed humans’ perception. These algorithms thus have the potential to learn new rules from data.
While coding skills are not a prerequisite, participants will get some hands-on coding experience by applying a case study in groups and, accompanied by experts reflecting on the results. This Master Class equips participants with a better understanding of which tasks are suitable for unsupervised machine learning and of how to interpret performance metrics.
Target Group
This Master Class is aimed at financial industry practitioners who work in risk management or compliance or who are involved in machine learning projects. At the same time, the course is designed to provide all interested parties valuable insights into the world of machine learning, and to offer some initial hands-on coding experience.
SAQ Recertification
This SFI Master Class is an acknowledged SAQ recertification measure for CWMA, CCoB, Affluent-, SME-, and Individual Client Advisor profiles and comprises four learning hours (4 credits).