# Calculate specificity (true negative rate) in crossvalidation in AutoMLPipeline

**URL:** <https://discourse.julialang.org/t/calculate-specificity-true-negative-rate-in-crossvalidation-in-automlpipeline/77958>\
**Category:** Machine Learning\
**Tags:** question\
**Created:** [March 16, 2022, 10:21am UTC](https://discourse.julialang.org/t/calculate-specificity-true-negative-rate-in-crossvalidation-in-automlpipeline/77958 "2022-03-16T10:21:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Michele\_Avanzo](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/michele_avanzo/32/34597_2.png) [@Michele\_Avanzo](https://discourse.julialang.org/u/Michele_Avanzo)\
**Post date:** [March 16, 2022, 10:21am UTC](https://discourse.julialang.org/t/calculate-specificity-true-negative-rate-in-crossvalidation-in-automlpipeline/77958/1 "2022-03-16T10:21:08Z")

</div>

Hi all,  
I am used to calculate sensitivity and specificity in classification problems. Sensitivity is recall, so not a problem, but specificity (true negative) is usually not included in evaluation metrics.  
Is it possible to calculate the specificity, or true negative rate, of a ML pipeline from crossvalidate ? I am following the tutorial from [https://github.com/IBM/AutoMLPipeline.jl](https://github.com/IBM/AutoMLPipeline.jl)