hardMultiple Choice
AIF-C01 Practice Question: Use a rules-based approach to approve loan…
A company wants to use a rules-based approach to approve loan applications but finds that it cannot keep up with changing regulations. They have historical data with decisions. Which approach should they adopt?
⚠ Common exam trap
AWS often tests the distinction between supervised and unsupervised learning by presenting a scenario where historical labels exist, tempting candidates to choose unsupervised clustering (Option D) because they confuse 'grouping similar applications' with 'predicting approval decisions.'
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Train a supervised machine learning model on historical decisions
Supervised machine learning can automatically learn patterns from historical loan decision data, adapting to changing regulations without manual rule updates. By training a model on labeled examples of approved and rejected applications, the system can generalize to new cases and adjust as the underlying regulatory logic shifts over time, which is precisely the limitation of a static rules-based approach.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Train a supervised machine learning model on historical decisions
Why this is correct
A supervised model learns the mapping from applicant features to historical approve or decline decisions, capturing patterns that rules cannot express. Retraining on fresh data lets the model adapt as regulations shift, addressing the rigidity that made the rules-based approach unworkable.
- ✗
Continue refining the rules-based system manually
Why it's wrong here
Manually editing rules still requires a human to translate each regulatory change into conditions, so the maintenance burden and lag persist. Rules engines suit stable, auditable logic. With historical labelled decisions available, a machine learning classifier learns patterns and adapts as regulations shift through retraining.
- ✗
Implement a deep neural network without feature engineering
Why it's wrong here
A deep neural network without feature engineering is a black-box model that cannot adapt to changing regulatory logic without retraining on new labelled data, whereas the scenario requires a rules-based system that can be updated explicitly as regulations shift. It is tempting because neural networks excel at pattern recognition from historical decisions, which would be correct if the goal were to replicate past approval patterns rather than to maintain auditable, modifiable rules.
- ✗
Use unsupervised learning to cluster applications
Why it's wrong here
Clustering groups unlabelled data by similarity; it produces no decision rule and cannot map features to approve/decline outcomes, so it cannot track regulatory changes. It is tempting because historical decisions exist, but clustering suits exploratory segmentation, not supervised classification where labelled outcomes drive predictions.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.