A STATISTICAL PERSPECTIVE ON DATA MINING

Data mining can be regarded as a collection of methods for drawing inf erences from data. The aims of data mining, and some of its methods, o verlap with those of classical statistics. However, there are some phi losophical and methodological differences. We examine these difference s, and we describe three approaches to machine learning that have deve loped largely independently: classical statistics, Vapnik's statistica l learning theory, and computational learning theory. Comparing these approaches, we conclude that statisticians and data miners can profit by studying each other's methods and using a judiciously chosen combin ation of them.