Fallout Precision

From GM-RKB
(Redirected from Fallout)
Jump to navigation Jump to search

A Fallout Precision is an Information Retrieval Evaluation Measure that is used to determine the proportion of non-relevant documents retrieved by the query.



References

2018a

  • (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Evaluation_measures_(information_retrieval)#Fall-out Retrieved:2018-2-16.
    • The proportion of non-relevant documents that are retrieved, out of all non-relevant documents available: : [math]\displaystyle{ \mbox{fall-out}=\frac{|\{\mbox{non-relevant documents}\}\cap\{\mbox{retrieved documents}\}|}{|\{\mbox{non-relevant documents}\}|} }[/math] In binary classification, fall-out is closely related to specificity and is equal to [math]\displaystyle{ (1-\mbox{specificity}) }[/math] . It can be looked at as the probability that a non-relevant document is retrieved by the query.

      It is trivial to achieve fall-out of 0% by returning zero documents in response to any query.

2018b

  • (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Information_retrieval#Fall-out Retrieved:2018-2-17.
    • The proportion of non-relevant documents that are retrieved, out of all non-relevant documents available: : [math]\displaystyle{ \mbox{fall-out}=\frac{|\{\mbox{non-relevant documents}\}\cap\{\mbox{retrieved documents}\}|}{|\{\mbox{non-relevant documents}\}|} }[/math] In binary classification, fall-out is closely related to specificity and is equal to [math]\displaystyle{ (1-\mbox{specificity}) }[/math] . It can be looked at as the probability that a non-relevant document is retrieved by the query.

      It is trivial to achieve fall-out of 0% by returning zero documents in response to any query.

2008

2001

2000