An introduction to ML and Model Risk

5 days

ML techniques for

  Scorecards
  Early warning signals
  Fraud
  Affordability models


Validating AI models

  Overview of main changes relative to classical models
  Tools for documentation


Quantifying model uncertainty and model risk

  General principles and theory
  Leveraging ML to sample parameters and models
  Bayesian neural nets


Detecting data quality issues

  Auto-encoders
  GANs
  LSTM networks

Interested in a demo?

Lorem ipsum dolorem et arceopara bellum. Lorem ipsum dolorem et arceopara bellum. Lorem ipsum dolorem et arceopara bellum.