In this webinar, we:
- Introduce the current state of machine learning in finance, highlighting its successes and failures.
– While machine learning excels in static closed-looped systems, such as board games, most financial systems are dynamic, continuously changing in nature. This leads to many issues, including overfitting and spurious correlations
– Current ML requires a trade off between explainable models (such as linear) or high performing models (like DNNs). It is hard to get both.
- Introduce Causal AI and explain how it can overcome many of the limitations of current ML and share case studies of how it is currently proving that in production.
- Give a product demo to show how Causal AI can be used to explain the relationships driving portfolio performance, simulate different scenarios that can affect performance and optimize portfolios.
Demo only – The First Causal Portfolio Optimizer: