A food service company wants to develop an ML model to help decrease daily food waste and increase sales revenue. The company needs to continuously improve the model's accuracy. Which solution meets…

Question

Options

• AUse Amazon SageMaker and iterate with newer data.
• BUse Amazon Personalize and iterate with historical data.
• CUse Amazon CloudWatch to analyze customer orders.
• DUse Amazon Rekognition to optimize the model.

• A
  88% (35)
• B
  3% (1)
• C
  8% (3)
• D
  3% (1)

Explanation

Explanation

Amazon SageMaker is the purpose-built ML platform on AWS that allows companies to build, train, and continuously retrain custom models using fresh data - making it ideal for a food waste prediction use case that requires ongoing accuracy improvements as customer patterns evolve. Option B is incorrect because Amazon Personalize is designed for recommendation engines (e.g., product suggestions), not for forecasting operational metrics like food waste, and historical data alone won't support continuous improvement. Option C is incorrect because Amazon CloudWatch is a monitoring and logging service, not an ML tool - it can track metrics but cannot build or improve predictive models. Option D is incorrect because Amazon Rekognition is a computer vision service focused on image and video analysis, which has no relevance to food waste forecasting or sales optimization.

Memory Tip

Think "SageMaker = Custom ML, Iterate Forever." Whenever an exam question mentions a custom ML model that needs continuous improvement with new data, SageMaker is almost always the answer. The keyword "continuously improve" signals you need a full ML lifecycle platform - only SageMaker provides that end-to-end capability.

No community discussion yet for this question.