Date Added: May 2012
Data warehouses form the basis for performing data mining tasks such as classification and clustering. A data warehouse is constructed from multiple databases. Whenever the databases are updated, they are not immediately applied to the data warehouse. Typically updates are collected and applied to the data warehouse periodically. Then all patterns derived from the data warehouse by some mining algorithm have to be updated as well. It is not feasible to combine the updates with the old data and perform any data mining task on the entire data for every updates. Due to the very large size of the databases it is highly desirable to perform these updates incrementally.