Unsupervised learning
Unsupervised learning looks for structure in data that has no labels: grouping similar customers, spotting unusual transactions, or finding topics in a pile of documents. Nobody tells the model what the right answer is.
In one line, for a 12-year-old
Unsupervised learning is sorting a big box of Lego by yourself, without anyone telling you the groups.
An example
A news site groups thousands of articles into story clusters so readers see one entry per event.
Why it matters to people
Groupings made by machines can turn into labels about people ("high-risk", "low-value"). Ask how a group was defined before you act on it.