Courseiva

AI-900 Practice Question: Describe Artificial Intelligence workloads and considerations

Which of the following scenarios is an example of a recommendation system AI workload?

⚠ Common exam trap

Test-takers frequently confuse a prerequisite (storing data in a database, Option C) with the AI workload itself, or mistake a simple rule-based system (spelling checker) for a recommendation engine, when the key differentiator is the use of historical user behavior to generate personalized predictions.

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

A music streaming service suggesting new songs based on listening history

A recommendation system AI workload analyzes user behavior (e.g., listening history) to predict and suggest new items (songs) that the user is likely to enjoy. This is a classic example of a collaborative filtering or content-based filtering model, which is a core AI workload under the 'Predictive' or 'Personalization' category.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • A spelling checker that identifies misspelled words in a document

    Why it's wrong here

    A spelling checker identifies misspelled words by comparing tokens against a dictionary or language model, often using edit distance, n-gram probabilities, or neural language modeling for context. This is a rule-based or error-correction task focused on text accuracy, not on predicting a user's future choices from behavioral history. Recommendation systems solve the different problem of ranking items according to a user's inferred tastes, so the underlying purpose and ML paradigm are unrelated.

  • A music streaming service suggesting new songs based on listening history

    Why this is correct

    A music streaming service that suggests new songs from listening history is a canonical recommendation system. It employs collaborative filtering, content-based filtering, or hybrid models that analyze user-item interactions, such as play counts, skips, and genre preferences, to predict the likelihood of a user enjoying unseen tracks. The system continuously updates its model as new listening behavior accrues, making it a classic example of AI-driven recommendation rather than simple retrieval.

  • A database storing customer purchase history

    Why it's wrong here

    A relational or NoSQL database that stores purchase history performs data persistence, indexing, and querying operations. Storing transactional rows is simply the ingestion layer that provides raw material for analytics. A recommendation system, by contrast, applies machine learning techniques like collaborative filtering or association rules to that historical data to infer preferences and generate personalized product suggestions. The database itself lacks any predictive logic.

  • A barcode scanner at a checkout counter

    Why it's wrong here

    A barcode scanner uses laser or image-based decoding to read UPC/EAN codes and map them to product records. That is a perceptual, lookup-oriented computer vision task, not a predictive algorithm. While product identification can feed downstream analytics, the scanner itself does not learn from user behavior or anticipate what a customer might buy next, which is the core function of a recommendation system.

About these practice questions

This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 practice question is part of Courseiva's free Microsoft 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 AI-900 exam.