Amazon AIF-C01 Exam - Topic 1 Question 29 Discussion

The company needs to automatically group similar customers and products based on their characteristics, which is a clustering task. Unsupervised learning is the ML strategy for grouping data without labeled outcomes, making it ideal for this requirement.

Exact Extract from AWS AI Documents:

From the AWS AI Practitioner Learning Path:

'Unsupervised learning is used to identify patterns or groupings in data without labeled outcomes. Common applications include clustering, such as grouping similar customers or products based on their characteristics, using algorithms like K-means or hierarchical clustering.'

(Source: AWS AI Practitioner Learning Path, Module on Machine Learning Strategies)

Detailed

Option A: Unsupervised learningThis is the correct answer. Unsupervised learning, specifically clustering, is designed to group similar entities (e.g., customers or products) based on their characteristics without requiring labeled data.

Option B: Supervised learningSupervised learning requires labeled data to train a model for prediction or classification, which is not applicable here since the task involves grouping without predefined labels.

Option C: Reinforcement learningReinforcement learning involves training an agent to make decisions through rewards and penalties, not for grouping data. This option is irrelevant.

Option D: Semi-supervised learningSemi-supervised learning uses a mix of labeled and unlabeled data, but the task here does not involve any labeled data, making unsupervised learning more appropriate.

AWS AI Practitioner Learning Path: Module on Machine Learning Strategies

Amazon SageMaker Developer Guide: Unsupervised Learning Algorithms (https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html)

AWS Documentation: Introduction to Unsupervised Learning (https://aws.amazon.com/machine-learning/)