Discovery of Association Rules at Multiple Levels

Data mining is extraction of implicit, previously unknown; potentially use for information from the vast amount of data available in the data sets (databases, data warehouses or other information repositories). In previous studies the association rules are generated at the single conceptual levels however mining association rules at multiple concept levels may lead to the discovery of more specific and concrete knowledge from large transaction databases by extension of some existing rules mining techniques. In multilevel association rules we use different minimum support for different conceptual levels. In this paper, multiple-level association rules are discussed using MLT2 algorithm. This algorithm discovers association rules for successive levels making use of rules already discovered for upper levels of concept hierarchy.