Changing experiment parameters is a good way to iterate on a Use Case. Before starting to model, you can change a variety of settings:

![](images/wb-exp-30.png)

&nbsp;  | Setting | To change...
------- | ------- | ---------
![](images/icon-wb-1.png)  | Positive class | _For binary classification projects only._ The class to use when a prediction scores higher than the classification threshold.
![](images/icon-wb-2.png)  | [Modeling mode](#change-modeling-mode) | The modeling mode, which influences the blueprints DataRobot chooses to train.        
![](images/icon-wb-3.png)  | [Optimization metric](#change-optimization-metric) | The optimization metric to one different from DataRobot's recommendation.
![](images/icon-wb-4.png)  | [Training feature list](#change-feature-list-pre-modeling) | The subset of features that DataRobot uses to build models.
