Cross-validation is a term that plays an important role primarily in the fields of Artificial Intelligence, Big Data and Smart Data, and Digital Transformation.
Cross-validation refers to a method where a computer-based model – for example, an artificial intelligence designed to analyse images or texts – is tested in a very specific way. The aim is to find out how good the model really is and how reliably it performs with new, unknown data.
Imagine you have a large table of data, such as thousands of customer entries. Instead of training the model with just a part of this data and testing with the rest, cross-validation involves splitting the entire dataset differently multiple times. Each time, the model is trained with one part and then its performance is checked using the remaining part. This provides a much more accurate picture of how reliable the model is in practice.
Cross-validation helps to avoid a model being evaluated too „optimistically“ because it happens to fit a specific dataset particularly well. Companies use this method to make better decisions when developing artificial intelligence and data-driven solutions.
Deutsch 
English (UK)