Study of various mathematical and statistical aspects of data mining. Includes supervised learning (regression, classification, and support vector machines) and unsupervised learning (clustering, principal components analysis, and dimensionality reduction). Uses technical tools drawn from linear algebra, multivariate statistics, and optimization. Three lecture hours a week for one semester. Statistics and Data Sciences 391D and Statistics and Scientific Computation 391D may not both be counted. Prerequisite: Graduate standing and a linear algebra course.