Resumen
Data mining is an application-driven field where research questions tend to be motivated by real-world data sets. In this context, a broad spectrum of formalisms and techniques has been proposed by researchers in a large number of applications. Organizing the data is inherently difficult. Classical problems in data analysis involving multivariate data include classification, regression, clustering and density estimation. The dimensionality "d" of vectors "x" plays a significant role in multivariate modeling. Recent research as of August 1, 2002 has shown that combining different models can be effective in reducing the instability that results from predictions using a single model fit to a single set of data. The navigation patterns of web surfers obtained from web logs also represent opportunities for prediction, clustering, personalization and related mining techniques often referred to as web mining. The term "data stream" pertains to data arriving overtime, in a nearly continuous fashion. In such applications, the data is often available for mining only once, as it flows by. Data streams have prompted several challenging research problems, including how to compute aggregate counts and summary statistics from such data