Skip to main content
Cross Validated

Return to Question

Tweeted twitter.com/StackStats/status/846379880975622144
formatting
Source Link
Chill2Macht
Chill2Macht
  • 6.5k
  • 5
  • 30
  • 62

I am using currently random forest and SVM for a binary classification problem. Especially with random forest it's easy to get the importance of all variables. 

But is it also possible to get the relevance for each variable in individual predictions? 

I don't need a detailed rule how the result was calculated, but which variable to look at would be very useful for example when using the model for fraud prediction or predictions of failures. Thanks!

I am using currently random forest and SVM for a binary classification problem. Especially with random forest it's easy to get the importance of all variables. But is it also possible to get the relevance for each variable in individual predictions? I don't need a detailed rule how the result was calculated, but which variable to look at would be very useful for example when using the model for fraud prediction or predictions of failures. Thanks!

I am using currently random forest and SVM for a binary classification problem. Especially with random forest it's easy to get the importance of all variables. 

But is it also possible to get the relevance for each variable in individual predictions? 

I don't need a detailed rule how the result was calculated, but which variable to look at would be very useful for example when using the model for fraud prediction or predictions of failures.

Source Link
MikeHuber
MikeHuber
  • 1.2k
  • 3
  • 14
  • 24

Interpret predictions of black box models

I am using currently random forest and SVM for a binary classification problem. Especially with random forest it's easy to get the importance of all variables. But is it also possible to get the relevance for each variable in individual predictions? I don't need a detailed rule how the result was calculated, but which variable to look at would be very useful for example when using the model for fraud prediction or predictions of failures. Thanks!