How to Continuously Improve an ML Model to Decrease Food Waste?
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 these requirements?
Community Votes
100% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.
Community Insight
This question tests your ability to distinguish between general-purpose ML platforms (SageMaker) and specialized services (Personalize, Rekognition), emphasizing that continuous model improvement requires retraining with new data.
Amazon SageMaker is the correct choice for building, training, and continuously iterating on machine learning models with newer data to improve accuracy over time. Community candidates unanimously agree that SageMaker's end-to-end ML capabilities best meet the requirement of ongoing model refinement.
Candidates often choose Amazon Personalize, mistakenly associating 'increase sales revenue' with recommendation systems, but Personalize is limited to personalization use cases and does not address the broader goal of reducing food waste with a continuously improving custom model.
Community Discussion (3 comments)
Comments & Corrections
No comments yet — spotted an error or have a note? Share it below.
Expert Analysis
Why Amazon SageMaker is the Correct Answer
The scenario requires a machine learning model that can be continuously improved using newer data to reduce food waste and increase sales revenue. Amazon SageMaker is a fully managed service that provides end-to-end capabilities for building, training, deploying, and iterating on custom ML models. It natively supports MLOps practices such as retraining pipelines, model monitoring, and automatic model updates when new data becomes available.
Why the Other Options Are Incorrect
- Option B – Amazon Personalize: This is a managed service specifically designed for building recommendation engines (e.g., product recommendations, personalized rankings). It is not a general-purpose ML platform and cannot be used to build a custom model for forecasting food demand or reducing waste.
- Option C – Amazon CloudWatch: CloudWatch is a monitoring and observability service for logs, metrics, and alarms. It does not build or train ML models.
- Option D – Amazon Rekognition: Rekognition is a pre-trained computer vision service for image and video analysis (e.g., face detection, object labeling). It cannot be used to develop a custom forecasting or optimization model for food waste.
Community Consensus
All community voters selected Option A, noting that SageMaker's ability to iterate with newer data is exactly what the company needs to continuously improve model accuracy over time.
Official Reference
Exam Strategy
When a question mentions 'continuously improve model accuracy' or 'iterate with new data,' immediately look for a general-purpose ML platform like Amazon SageMaker. Eliminate specialized AI services (Rekognition, Personalize, Comprehend) unless the use case explicitly matches their narrow functionality.
Related Analysis
Practice All AIF-C01 Questions
Access 100 questions with complete answers and detailed explanations.
View Full AIF-C01 Practice Test →