A type of machine learning that looks for previously undetected patterns in a data set with no pre-existing labels and with a minimum of human supervision.
Unsupervised Learning algorithms find clusters and structure in raw, unlabeled data. In the enterprise, they are commonly used for anomaly detection, flagging subtle deviations in network traffic or factory floor telemetry that engineers do not have time to review manually.
See also Enterprise Architecture, Large Language Model, Fine-Tuning and Model Inference.