AWS Certified AI Practitioner

Explanation

Correct Answer: B) Supervised learning

Why this is correct:

1. Labeled Data: The problem explicitly mentions "historical labeled data" where customers are labeled as "default" or "non-default." This is the key characteristic of supervised learning.
2. Classification Task: Predicting whether a customer will default or not is a binary classification problem, which falls under supervised learning.
3. Training Process: In supervised learning, the model learns from labeled examples (input-output pairs) to make predictions on new, unseen data.

Why other options are incorrect:

• A) Unsupervised learning: This is used when there are no labels in the data. The algorithm tries to find patterns or structure in the data without predefined categories.
• C) Transfer learning: This involves using knowledge gained from solving one problem to help solve a different but related problem. While it can be used with supervised learning, it's not the primary method for this specific scenario.
• D) Reinforcement learning: This involves an agent learning through trial and error by interacting with an environment and receiving rewards or penalties. It's not suitable for this classification problem with historical labeled data.

Key Takeaway: When you have labeled historical data and want to predict outcomes based on that data, supervised learning is the appropriate machine learning approach.