AI0-001 AI Security, Ethics and Governance Practice Question
A company uses a machine learning model to recommend products to customers. The marketing team notices that the model is recommending high-profit items more frequently than low-profit items, even when customers are likely to prefer the latter. This behavior is causing customer dissatisfaction. Which approach would best align the model with customer preferences while maintaining profitability?
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
✓
Use a multi-objective optimization framework to balance profit and customer satisfaction.
A multi-objective optimization framework explicitly allows the model to balance multiple goals, such as profit and customer satisfaction, by optimizing both objectives simultaneously. Option A is incorrect because weighting profit more heavily would exacerbate the issue and further ignore customer preferences. Option C is incorrect because adjusting hyperparameters to reduce profit feature influence is not a principled way to balance objectives and may not effectively improve satisfaction. Option D is incorrect because removing profit data entirely ignores legitimate business goals, potentially harming profitability.
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 the model with a loss function that weights profit more heavily than customer satisfaction.
Why it's wrong here
Weighting profit above customer satisfaction in the loss function directly optimises the behaviour the marketing team is complaining about, worsening the dissatisfaction rather than aligning recommendations with preference. Such weighting suits scenarios where revenue maximisation is the sole objective and preference signals are deliberately subordinate.
- ✓
Use a multi-objective optimization framework to balance profit and customer satisfaction.
Why this is correct
Multi-objective optimisation explicitly optimises two competing objectives simultaneously, so profit and customer satisfaction are traded off rather than profit dominating. This directly addresses the stem's constraint: high-profit recommendations overriding genuine customer preference, restoring alignment without abandoning profitability.
- ✗
Adjust the model's hyperparameters to reduce the influence of profit features.
Why it's wrong here
Hyperparameters govern learning dynamics such as learning rate and regularisation strength, not the semantic weighting of individual input features like profit. Tuning them cannot rebalance profit against preference. Feature weighting belongs to feature engineering or the loss function, so this is the right lever only when the model architecture itself needs tuning.
- ✗
Remove profit data from the training set and only use customer preference data.
Why it's wrong here
Deleting profit data removes the profitability constraint entirely, so recommendations can no longer be balanced against margin and the stated requirement to maintain profitability fails. Preference-only training fits pure relevance or engagement ranking, where commercial return is not a modelling objective at all.
About these practice questions
One of 962 original AI0-001 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 AI0-001 practice question is part of Courseiva's free CompTIA 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 AI0-001 exam.