[
https://issues.apache.org/jira/browse/SPARK-10697?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15470104#comment-15470104
]
Yashwanth Kumar edited comment on SPARK-10697 at 9/7/16 9:33 AM:
-----------------------------------------------------------------
Yes [~dmueller1607]. Exactly as you told, We need Lift as another measure of
Rule along with confidence. Confidence of a Rule X-> Y will only take X and Y
occurrence and X into account. This does not truly implicate the relationship
between X and Y.
Lift calculates how much X and Y are really related rather than coincidental.
It measures the frequent occurrence of X and Y if they are Statistically
independent of one another.
Lift=Support(X and Y)/Support(X)*Support(Y) ( or ) Confidence(X and Y)/
Support(Y)
was (Author: yashkumar1992):
As discussed, Lift is one of the necessary measure that eliminates the concern
of random occurrence of a rule.
> Lift Calculation in Association Rule mining
> -------------------------------------------
>
> Key: SPARK-10697
> URL: https://issues.apache.org/jira/browse/SPARK-10697
> Project: Spark
> Issue Type: New Feature
> Components: MLlib
> Reporter: Yashwanth Kumar
> Priority: Minor
>
> Lift is to be calculated for Association rule mining in
> AssociationRules.scala under FPM.
> Lift is a measure of the performance of a Association rules.
> Adding lift will help to compare the model efficiency.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
