Semantic interestingness measures for discovering association rules in the skeletal dysplasia domain

Table 1 Experimental results on finding the quality of association rules, discovered using traditional interestingness measures

Traditional	Accuracy	Accuracy	Accuracy	Accuracy	Accuracy
interestingness measures	K = 1	K = 2	K = 3	K = 4	K = 5
Confidence	28.77	46.58	53.42	54.79	57.33
Lift	26.03	36.99	42.47	49.32	57.53
Conviction	28.77	43.84	46.58	49.32	57.53
Correlation coefficient	27.40	36.99	45.21	52.05	57.53
Cosine	28.76	43.84	49.31	54.79	58.90
Jaccard	31.51	45.21	52.05	54.79	57.53
Leverage	24.66	35.62	46.58	54.79	57.53

The voting strategy has been used as classification method and the association rules have been used as background knowledge.

ISSN: 2041-1480