AWS Certified Machine Learning – Specialty — Question 113

A Data Scientist received a set of insurance records, each consisting of a record ID, the final outcome among 200 categories, and the date of the final outcome.
Some partial information on claim contents is also provided, but only for a few of the 200 categories. For each outcome category, there are hundreds of records distributed over the past 3 years. The Data Scientist wants to predict how many claims to expect in each category from month to month, a few months in advance.
What type of machine learning model should be used?

Answer options

• A. Classification month-to-month using supervised learning of the 200 categories based on claim contents.
• B. Reinforcement learning using claim IDs and timestamps where the agent will identify how many claims in each category to expect from month to month.
• C. Forecasting using claim IDs and timestamps to identify how many claims in each category to expect from month to month.
• D. Classification with supervised learning of the categories for which partial information on claim contents is provided, and forecasting using claim IDs and timestamps for all other categories.

Correct answer: C

Explanation

The correct answer is C because forecasting is the appropriate model for predicting future values based on past data, specifically looking at trends over time with claim IDs and timestamps. Option A focuses on classification rather than forecasting future claims, while B suggests reinforcement learning, which is not suitable for this predictive task. Option D combines classification and forecasting but does not provide a direct approach for all categories, making it less effective than a pure forecasting model.