The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

what is the meaning of "ROC(Threshholds)"?

lg21c
lg21c Member Posts: 24 image Contributor II
in Help
what is the meaning of "ROC(Threshholds)"? See Picture Below

It is the result of process "Jump to Tutorial Process" of operator "Performance"

Answers

  • MartinLiebig
    MartinLiebig Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,533 image RM Data Scientist
    Hi,
    in order to get a certain TPR/FPR (the red curve) you need to apply a certain confidence threshold. Thats the blue curve.

    Cheers,
    Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • lg21c
    lg21c Member Posts: 24 image Contributor II
    hi@mschmitz ，what is the meaning of the  x-axis of  ROC(Threshholds) curve？
  • yyhuang
    yyhuang Administrator, Employee-RapidMiner, RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 364 image RM Data Scientist
    Hi @lg21c, the x-axis of ROC is false positive rate. We want to have a model that reach a high true positive rate while a low false positive rate, the lower the better. More definitions: http://www.damienfrancois.be/blog/files/modelperfcheatsheet.pdf
    Cheers,
    YY
  • lg21c
    lg21c Member Posts: 24 image Contributor II
    edited April 2021
    Hi@mschmitz , is the  x-axis of  ROC(Threshholds) curve false positive rate ,too? 
    seem not to be

Categories