Discover all of the brand-new features and improvements to existing capabilities in the Dataiku 11.3 updateLET'S GO

Hyperparameter Tuning // Grid Search Always Picking Biggest Numbers

emrek
Level 2
Hyperparameter Tuning // Grid Search Always Picking Biggest Numbers

I am using Random Forest algorithm. Also, I am trying tune hyperparameters by using Grid Search. Grid Search picking biggest number hyperparameters all the time. I am sharing a pictures about my problem. Is there any reason of this problem?

 


Picture 1.pngPicture 2.png

0 Kudos
3 Replies
MiguelangelC
Dataiker

Hi,

There is not a problem here as far as we can see.

In training the model, it was found the 'biggest numbers' provide better results. This is also mentioned in the uploaded screenshot:'Higher values generally increase the quality of the prediction'.

Rickh008
Level 3

Have you tested against the model using validation/hold-out dataset?

A more generalized model may perform better with new data. It's unsurprising that a more advanced model performs better on training/test data.

0 Kudos
emrek
Level 2
Author

Hi, yes i did.  I was thinking that biggest number always can't be best one for model. I am sharing my project flow and hyperparameter optimization for random forest model. We can clearly see line is always going up on hyperparameter optimization plot.

0 Kudos