Visualization to facilitate association rules modelling: A review

Association rules modelling is one of most widely used data mining modelling tools; it finds interesting associations or correlation relationships among a set of data attributes. One of the major problems with association rules modelling, however, is the overwhelming number of rules that can be generated, many of which may not be interesting. This paper surveys the current state of art in application of visualization techniques to facilitate association rules modelling process in terms of visualization of derived rules, visualization of rule evaluation, and visual interactive rule derivation. A number of issues that have been overlooked and areas that need to be improved are identified through reviewing a collection of related research and examining four current data mining softwares with respect to their design of a few important visualization features to support association rules modelling. Key words: data mining, visualization, association rules Address for correspondence