Unsupervised learning
Learning from data without given answers – the model discovers structure on its own.
In unsupervised learning there are no labels. The model independently looks for patterns, groups or anomalies, such as customer segments in purchase data or unusual transactions.
Closely related is self-supervised learning, which is used to pre-train large language models: the model creates its own learning task, for example by predicting the next word of a text.
General information, not legal or professional advice.