exam questions

Exam AWS Certified Machine Learning - Specialty All Questions

View all questions & answers for the AWS Certified Machine Learning - Specialty exam

Exam AWS Certified Machine Learning - Specialty topic 1 question 295 discussion

A data scientist receives a collection of insurance claim records. Each record includes a claim ID. the final outcome of the insurance claim, and the date of the final outcome.

The final outcome of each claim is a selection from among 200 outcome categories. Some claim records include only partial information. However, incomplete claim records include only 3 or 4 outcome categories from among the 200 available outcome categories. The collection includes hundreds of records for each outcome category. The records are from the previous 3 years.

The data scientist must create a solution to predict the number of claims that will be in each outcome category every month, several months in advance.

Which solution will meet these requirements?

  • A. Perform classification every month by using supervised learning of the 200 outcome categories based on claim contents.
  • B. Perform reinforcement learning by using claim IDs and dates. Instruct the insurance agents who submit the claim records to estimate the expected number of claims in each outcome category every month.
  • C. Perform forecasting by using claim IDs and dates to identify the expected number of claims in each outcome category every month.
  • D. Perform classification by using supervised learning of the outcome categories for which partial information on claim contents is provided. Perform forecasting by using claim IDs and dates for all other outcome categories.
Show Suggested Answer Hide Answer
Suggested Answer: C 🗳️
Community vote distribution
C (70%)
D (30%)

Comments

Chosen Answer:
This is a voting comment. You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
2eb8df0
1 day, 1 hour ago
Selected Answer: C
D is the better answer, except for the part that says "for all other outcome categories". It should say, "for all outcome categories" including the ones we categorized with partial information. Because of this flaw, i go C.
upvoted 1 times
...
CW0106
6 months ago
Selected Answer: D
Should be D
upvoted 1 times
...
Peter_Hsieh
10 months, 2 weeks ago
Selected Answer: D
For the outcome categories with partial information (3 or 4 out of 200 categories), supervised learning can be used to classify claims into those categories based on the available claim contents. For the remaining outcome categories without partial information, forecasting techniques using claim IDs and dates can be employed to predict the expected number of claims in each category every month.
upvoted 2 times
...
F1Fan
10 months, 3 weeks ago
While the argument for option C is valid in terms of using claim IDs and dates for forecasting, it does not address the scenario where partial information on claim contents is available for some outcome categories. By ignoring this information, option C may miss an opportunity to improve the accuracy of predictions for those categories through classification techniques. Furthermore, various machine learning resources and best practices recommend combining different techniques, such as classification and forecasting, when dealing with complex datasets that contain both structured and unstructured data. This hybrid approach can often lead to more accurate and robust solutions.
upvoted 1 times
...
AIWave
1 year ago
Selected Answer: C
A: No - not a classification problem B: No - Reinforcement learning does not apply to the situation - adding positive reinforcement/negative penalty to train the system does not apply C: Yes - leverages historical data (claim IDs and dates from the previous 3 years) to forecast future claim counts D: Not a classification problem C:
upvoted 2 times
...
vkbajoria
1 year ago
Selected Answer: C
this is forecasting problem
upvoted 2 times
...
kyuhuck
1 year, 1 month ago
Selected Answer: C
C directly addresses the need to forecast the number of claims in each outcome category on a monthly basis, leveraging historical data patterns without the need for classifying individual claim records based on their content.
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
Warsaw, 1 minute ago