Non-parametric Bayesian models are particularly at home in the areas of big data and smart data, artificial intelligence and digital transformation. They are used when very large amounts of data need to be analysed and little is known about the structure of the data beforehand.
In contrast to traditional (parametric) models, in which the number of patterns or groups to be detected in the data must be specified, non-parametric Bayesian models are flexible. They automatically adapt to the complexity of the data and find out for themselves how many structures or categories are actually present.
An illustrative example: Imagine you run an online shop with thousands of products. You want to find out how many different customer groups there are without defining them in advance. Non-parametric Bayesian models automatically group customers based on their purchasing behaviour and identify new segments that were previously unknown, for example.
This makes your decisions more data-driven and more accurate. Non-parametric Bayesian models are therefore particularly useful when data volumes are large and you want to discover the correlations within them flexibly and without presettings.
Deutsch 
English (UK)