Abstract: A novel association rule mining algorithm is composed, using the unit cube chain decomposition structures introduced in HAN, 1966; TON, 1976. HAN, 1966 established the chain split theory. TON, 1976 invented an excellent chain computation framework which brings chain split into the practical domain. We integrate these technologies around the rule mining procedures. Effectiveness is related to the intention of low complexity of rules mined. Complexity of the procedure composed is complementary to the known Apriori algorithm which is defacto standard in rule mining area.

Keywords: Data mining, unite cube.

ACM Classification Keywords: 1.5. Pattern recognition, H.2.8 Database applications, Data mining.

Link:

CHAIN SPLIT AND COMPUTATIONS IN PRACTICAL RULE MINING

Levon Aslanyan, Hasmik Sahakyan

http://foibg.com/ibs_isc/ibs-08/ibs-08-p19.pdf