Mining Frequent Item sets in Data Streams

Abstract

From the last decade, data mining has become the key technique to analyze and understand the data. Typical data mining tasks include association mining, classification and clustering. These techniques help find interesting patterns, regularities and anomalies in the data. However traditional data mining techniques can not directly apply to the data streams. This is because mining algorithms developed in the past target disk-resident or in-core datasets, and usually makes several passes of the data. Mining data streams are allowed only one look at the data, and techniques have to keep pace with the arrival of new data. Furthermore, dynamic data streams pose new challenges, because their underlying distribution might be changing. Recently a number of algorithms focus on approximate one-pass algorithms, mining over dynamic data streams, and mining changes or trends in data streams.