MIRAGE: A framework for mining, exploring and visualizing minimal association rules Mohammed J. Zaki Benjarath Phoophakdee In this paper we propose the concept of minimal association rules, the most general rules that satisfy a given support and confidence threshold. We present MIRAGE, an new framework for mining and visually exploring the minimal rules. MIRAGE uses lattice-based interactive rule visualization approach, displaying the rules in a very compact form; all association rules can also be generated if desired. MIRAGE uses a database back-end to store the state of exploration for easy retrieval at a later point in time. Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY cs-03-04
MIRAGE: A framework for mining, exploring and visualizing minimal association rules
Mohammed J. Zaki
Benjarath Phoophakdee
In this paper we propose the concept of minimal association rules, the most general rules that satisfy a given support and confidence threshold. We present MIRAGE, an new framework for mining and visually exploring the minimal rules. MIRAGE uses lattice-based interactive rule visualization approach, displaying the rules in a very compact form; all association rules can also be generated if desired. MIRAGE uses a database back-end to store the state of exploration for easy retrieval at a later point in time.
Department of Computer Science, Rensselaer Polytechnic Institute, Troy, NY
cs-03-04