Deep learning is a powerful tool, which is becoming increasingly popular in financial modeling. However, model validation requirements such as SR 11-7 pose a significant obstacle to the deployment of neural networks in a bank's production system. Their typically high number of (hyper-)parameters...

This paper introduces a benchmark model for financial markets, which is based on the unique characterization of a benchmark portfolio that is chosen to be the growth optimal portfolio. The general structure of risk premia for asset prices and portfolios is derived. Furthermore, the short rate is...