Universal Containers (UC) has 10 models currently in production that are being used to predict across their org, UC is interested in understanding how well these 10 models are performing. What are the steps required to achieve this?
A.
Update the Models settings for the models and add a prediction field.
B.
Update the Model settings for the models and set a terminal state filter.
C.
Run the models against all the data currently in org to calculate their performance.
D.
Run the models against the dataset used to create the stories.
A : adding a prediction does not assess performance of already existing models
B : yes, enable monitoring performance, set terminal state, click on ANALYZE ACCURACY
C : not ALL the data, only subset determined by terminal state
D : that does not bring more information than already obtained
According to this Salesforce help article both A and B seems to be correct. I hate the bad wording of these questions...
https://help.salesforce.com/s/articleView?id=sf.bi_edd_model_manager_accuracy.htm&type=5
The article states that you first create a prediction field and then you set a terminal state by selecting an outcome field.
A voting comment increases the vote count for the chosen answer by one.
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one.
So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
snusmumrick
Highly Voted 2 years, 1 month agohananetest
Most Recent 8 months ago[Removed]
1 year, 4 months agoVolovitch
1 year, 11 months agosnusmumrick
2 years, 2 months agosnusmumrick
2 years, 2 months ago