An introduction notes that classification serves many objectives: the maintenance of institutional safety and order, provision of inmate protection and services, and the management of personnel and resources. Two basic components of institutional classification are the selection of risk factors and the formulation of decision rules. The article discusses risk factors currently in use, including consensus-based models, equity-based models, and selections based on empirical prediction and psychometric testing. Decision rules considered include linear additive point scales, decision trees, matrix classification, and attempts to integrate the objective and subjective aspects of classification. The author emphasizes that no one standardized classification can fit both jails and prisons, since populations, resources, policy orientations, and architectures differ substantially. Most current correctional classifications exhibit weaknesses in management, methodology, and implementation. The trend toward objective methods, however, has facilitated scientific evaluation and improvement through bootstrapping. Approximately 70 references. (Author abstract modified)