It’s an open secret that traditional portfolio optimisation theories fail in the real world. They are misled by spurious correlations in historical data and they magnify noise in the estimation of risk and returns. It’s perhaps less widely known that state-of-the-art machine learning approaches to portfolio construction fail for similar reasons.
This is especially problematic for portfolio managers in the current moment. Global markets are characterised by high uncertainty, amid divergent post-pandemic recovery scenarios. And long-standing correlations between asset classes are shifting and collapsing.
Causal AI provides new methods for portfolio optimisation that overcome these problems. Causal AI digs beneath correlations to identify causal signals and causal relationships between assets.
We demonstrate how this enables Causal AI to outperform all other approaches in terms of risk-adjusted returns. Leading asset managers are already benefiting from intelligent portfolio optimisation with Causal AI.
