Association rules, lift parameter
Hey, I have a process that extract association rules. I want to know how the lift parameter is interpreted?
According to the rapidminer tutorial:
"Values close to 1 imply that X and Y are independent and the rule is not interesting. "
So, are all generated rules in my process worthless as lift is close to 1? Which of them are interesting?
Best Answer
-
Hi @AliMajed
I suggest you looking at this article which has a great explanation of lift parameter: https://www.ibm.com/support/knowledgecenter/en/SSEPGG_9.5.0/com.ibm.im.model.doc/c_lift_in_an_association_rule.html
Namely, this consideratioons are important:
- A lift value greater than 1 indicates that the rule body and the rule head appear more often together than expected, this means that the occurrence of the rule body has a positive effect on the occurrence of the rule head.
- A lift smaller than 1 indicates that the rule body and the rule head appear less often together than expected, this means that the occurrence of the rule body has a negative effect on the occurrence of the rule head.
- A lift value near 1 indicates that the rule body and the rule head appear almost as often together as expected, this means that the occurrence of the rule body has almost no effect on the occurrence of the rule head.
From your example, all lift values are over 1, so all rules do make sense, but depending on lift value, some rules are actually 'stronger' than others.
4
Answers
-
Hi @AliMajed
I suggest you looking at this article which has a great explanation of lift parameter: https://www.ibm.com/support/knowledgecenter/en/SSEPGG_9.5.0/com.ibm.im.model.doc/c_lift_in_an_association_rule.html
Namely, this consideratioons are important:
- A lift value greater than 1 indicates that the rule body and the rule head appear more often together than expected, this means that the occurrence of the rule body has a positive effect on the occurrence of the rule head.
- A lift smaller than 1 indicates that the rule body and the rule head appear less often together than expected, this means that the occurrence of the rule body has a negative effect on the occurrence of the rule head.
- A lift value near 1 indicates that the rule body and the rule head appear almost as often together as expected, this means that the occurrence of the rule body has almost no effect on the occurrence of the rule head.
From your example, all lift values are over 1, so all rules do make sense, but depending on lift value, some rules are actually 'stronger' than others.
4