Data Mining

Catalog description

Data Mining is the process of discovering patterns, correlations, and trends, in large data sets. This course is designed to provide an overview of the data mining process, with an emphasis on data management, pattern discovery, and cluster analysis. Data management includes data selection, cleaning, clustering, visualization, and distributed data storage and processing. The course covers pattern mining concepts, including pattern discovery concepts, efficient pattern mining algorithms, and graph pattern mining. The classification problem is illustrated through decision tree algorithms and ensemble methods. Basic concepts of cluster analysis are introduced, followed by typical clustering algorithms, including partitioning methods, hierarchical clustering, and graph clustering. Applications of cluster analysis are also covered. The course concludes with a study of data mining in the context of graphs used to model a wide range of networks from social networks to biological networks to web pages on the Internet.