Causal machine learning is a term from the categories of artificial intelligence, big data, smart data and digital transformation. In contrast to conventional machine learning, which merely recognises correlations, causal machine learning aims to discover real cause-and-effect relationships.
This means that instead of just analysing the fact that people who frequently buy sportswear often also book fitness classes, Causal Machine Learning tries to find out whether buying sportswear really leads to someone booking classes later - or whether both things are perhaps influenced by another factor such as health awareness.
An illustrative example: A company wants to know whether a certain advertising campaign actually generates more sales. Traditional methods only show a correlation. Causal machine learning, however, checks whether the campaign is really the cause of the increase in sales - or whether there are other reasons behind it, such as a general trend movement.
This gives companies, especially decision-makers, a better basis for important business decisions and enables them to make more targeted investments in measures that have a demonstrably positive effect. Causal machine learning therefore provides greater clarity and certainty in a data-driven world.
Deutsch 
English (UK)