Clustering
In plain terms
Grouping similar data points together without labels.
Going deeper
Clustering partitions data into groups where members are more similar to each other than to other groups, an unsupervised task. It discovers natural groupings.
Under the hood
Algorithms (k-means, DBSCAN, hierarchical) differ in assumptions; choosing the number of clusters is tricky.
Examples
Customer segmentation, k-means, anomaly detection, image grouping.
Think of it like...
Like sorting a crowd into friend groups based on who naturally gathers together.