exam questions

Exam PL-200 All Questions

View all questions & answers for the PL-200 exam

Exam PL-200 topic 5 question 23 discussion

Actual exam question from Microsoft's PL-200
Question #: 23
Topic #: 5
[All PL-200 Questions]

A company is training an Al model using a custom table to determine the amount of time it takes to deliver a package based on several key fields.
The testing data used to train the model is used for all training and regression testing scenarios and is considered complete data.
The trained model predicts a 2 percent variance between the estimated delivery time and the actual delivery time of packages.
The executive sponsors reject the model because the actual variance is at 15 percent.
You need to address the sponsors' concern.
What should you do?

  • A. Replace the training data with real-world data.
  • B. Reduce the size of the data used within the model.
  • C. Increase the size of the data used with the model.
  • D. Use sample training data from Microsoft.
Show Suggested Answer Hide Answer
Suggested Answer: A 🗳️
Note: Start using AI Builder with sample data
Don't have any data of your own to create a model? No problem! We've got you covered.
Sample data is available for several AI Builder model types, together with instructions for working with the sample data.
Reference:
https://docs.microsoft.com/en-us/ai-builder/samples

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
zapex
Highly Voted 2 years, 5 months ago
Answer: A Best way to improve the performance of an AI model is by training it using real data. B. is counterproductive. C. will not work if the data is garbage. D. Sample triaing data from microsoft will not improve the performance of the model in real world.
upvoted 8 times
D365Apprentice
1 year, 11 months ago
Great summary of the answer here
upvoted 1 times
...
...
33a7f9e
Most Recent 7 months ago
A. Replace the training data with real-world data. Using real-world data for training the model can help improve its accuracy and performance.
upvoted 1 times
...
jkaur
1 year ago
correct
upvoted 1 times
...
jkaur
1 year ago
should be A
upvoted 1 times
...
Ikhalil
2 years, 1 month ago
A is correct
upvoted 1 times
...
AlineVasarevic
2 years, 5 months ago
This answers are very odd. I would training it again
upvoted 1 times
...
Clubsodas
2 years, 7 months ago
Not sure what the answer is. I read through this article : https://learn.microsoft.com/en-us/ai-builder/prediction-create-model?source=recommendations It seems like you want to select the most relevant columns (this could be decreasing the size of the data) but you also want to have enough data to train the model (this could be increasing the size of the data).
upvoted 1 times
Clubsodas
2 years, 7 months ago
If I had to make a guess, I'd say it's "Replace the training data with real-world data." because the question states trained model prediction vs. actual variance. If we assume that actual variance is using production data, then we would need to use the same dataset to make an accurate prediction.
upvoted 1 times
...
...
synalis
2 years, 8 months ago
shouldn't it be answer D "Use sample training data from Microsoft"?
upvoted 3 times
allesglar
2 years, 6 months ago
A) is correct. How exactly will sample data improve the accuracy of the model? Sample data are useful if you do not have any data at all.
upvoted 2 times
...
[Removed]
2 years, 5 months ago
lol what?
upvoted 2 times
...
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
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.

SaveCancel
Loading ...
exam
Someone Bought Contributor Access for:
SY0-701
London, 1 minute ago