Stochastic Cash Flow Models are at the heart of internal models for life insurance. They are used to project the payments to policy holders and future profits of the shareholders over the full duration of the contracts. However, the interactions of capital market scenarios, product features and management rules within a SCFM are complex and often difficult to comprehend. We will show a new approach using Machine Learning methods to analyse patterns in the SCFMs core outputs as Present Value of Future Profits. We will further give an introduction to classic ML methods and how they can be used to predict PVFPs in a given capital market scenario quickly. Finally, we will discuss the pros and cons of these new models vs. classical statistical models.