Causality in Banking and Financial Use Cases

Our CTO, Dr. Maksim Sipos, will be presenting the benefits of applying Causal AI to financial use-cases, as part of the Machine Learning Week organised by Predictive Analytics World.

Abstract:
Typical machine learning models fit historic data based on correlations. These models fail when environments change (for example when a macroeconomic regime shift occurs). Causal models are more robust and generalize better. However, inferring causality from data is hard. In this talk, Dr. Maksim Sipos will describe what techniques we use to build causal models and the benefits we have observed in consumer lending and portfolio risk use cases.