nerdexam
Amazon

MLS-C01 · Question #322

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…

The correct answer is C. Perform forecasting by using claim IDs and dates to identify the expected number of claims in. To predict the number of claims for each outcome category every month, several months in advance, a time-series forecasting solution is required.

Modeling

Question

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?

Options

  • APerform classification every month by using supervised learning of the 200 outcome categories
  • BPerform reinforcement learning by using claim IDs and dates. Instruct the insurance agents who
  • CPerform forecasting by using claim IDs and dates to identify the expected number of claims in
  • DPerform classification by using supervised learning of the outcome categories for which partial

How the community answered

(49 responses)
  • A
    6% (3)
  • B
    2% (1)
  • C
    90% (44)
  • D
    2% (1)

Why each option

To predict the number of claims for each outcome category every month, several months in advance, a time-series forecasting solution is required.

APerform classification every month by using supervised learning of the 200 outcome categories

Classification predicts the category of a single future claim, not the number of claims for each category in a future month.

BPerform reinforcement learning by using claim IDs and dates. Instruct the insurance agents who

Reinforcement learning is a paradigm for decision-making in dynamic environments, typically involving agents taking actions to maximize rewards, and is not suitable for predicting future counts of events based on historical data.

CPerform forecasting by using claim IDs and dates to identify the expected number of claims inCorrect

The requirement to predict the number of claims per category every month, several months in advance is a classic time-series forecasting problem. By using claim IDs and dates, the data can be aggregated monthly for each outcome category, and a forecasting model can then be applied to predict future claim volumes based on historical trends.

DPerform classification by using supervised learning of the outcome categories for which partial

Similar to choice A, classification predicts the category of a single claim and does not fulfill the requirement of predicting the number of claims for each category over time.

Concept tested: Time-series forecasting problem identification

Source: https://aws.amazon.com/what-is/time-series-forecasting/

Topics

#Forecasting#Time Series#Predictive Modeling#Problem Framing

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full MLS-C01 Practice