AI-900 Practice Exam 60 — 20 Questions

Question 1

A retail company has historical data about customers, including age, purchase history, and whether they have churned (yes/no). They want to train a model that predicts if a new customer will churn. Which type of machine learning should they use?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Supervised classification. The goal is to predict a categorical outcome (churn: yes/no) from historical labeled data. Supervised classification algorithms, such as logistic regression or decision trees, learn from input features (age, purchase history) and the target label (churn status) to assign new customers to one of the discrete classes. This directly matches the requirement for a binary classification model.

Answer

Supervised regression

Answer

Unsupervised clustering

Answer

Reinforcement learning

Question 2

What is machine learning?

Accepted Answer

A subset of AI where algorithms learn from data to make predictions without explicit programming. Machine learning is a subset of artificial intelligence (AI) that enables systems to automatically learn and improve from experience without being explicitly programmed for every scenario. Instead of following static rules, ML algorithms use training data to identify patterns and make predictions or decisions. This is the core definition tested in AI-900, distinguishing ML from traditional rule-based programming.

Answer

A process of manually programming computers with rules for every possible scenario

Answer

A method of creating robots that can perform physical tasks

Answer

A type of computer network for processing large datasets

Question 3

A company uses an AI system to automatically generate personalized email subject lines for marketing campaigns. The system has been trained on historical data that includes biased language patterns. The company wants to ensure the generated subject lines do not reinforce stereotypes based on gender, age, or ethnicity. Which Microsoft responsible AI principle should guide the selection and filtering of training data?

Accepted Answer

Inclusiveness. Inclusiveness, because this principle directly addresses the need to ensure AI systems treat all people fairly and avoid reinforcing stereotypes. By selecting and filtering training data to remove biased language patterns related to gender, age, or ethnicity, the company operationalizes inclusiveness to prevent the model from generating discriminatory subject lines. This principle guides the proactive mitigation of bias in data curation and model outputs.

Answer

Reliability and safety

Answer

Privacy and security

Answer

Transparency

Question 4

What is the difference between 'precision' and 'recall' as model evaluation metrics?

Accepted Answer

Precision measures correctness of positive predictions; recall measures coverage of actual positives. Precision measures the proportion of positive identifications that were actually correct (true positives / (true positives + false positives)), while recall measures the proportion of actual positives that were correctly identified (true positives / (true positives + false negatives)). In Azure Machine Learning, these metrics are critical for evaluating classification models, especially when dealing with imbalanced datasets, as they provide distinct insights into model performance.

Answer

Precision is the speed of prediction; recall is the model's memory usage

Answer

Precision and recall are both the same metric, just calculated on different datasets

Answer

Recall is higher than precision whenever the model has seen more training data

Question 5

What is 'ONNX' and why is it relevant to Azure AI?

Accepted Answer

An open model interchange format enabling models to move between frameworks and edge deployments. ONNX (Open Neural Network Exchange) is an open-source model interchange format that allows machine learning models to be transferred between different frameworks (e.g., PyTorch, TensorFlow, scikit-learn) and deployed across various environments, including edge devices. In Azure AI, ONNX is relevant because it enables interoperability and portability, allowing models trained in one framework to be optimized and run efficiently using Azure's ONNX Runtime, which accelerates inference on both cloud and edge hardware.

Answer

An Azure-specific machine learning programming language

Answer

A database for storing machine learning model training data

Answer

A Microsoft cloud service for distributed model training

Question 6

A retail company wants to build a solution that automatically reads the printed text on product labels to update inventory records. The labels contain alphanumeric characters and are in various fonts and sizes. Which Azure Cognitive Service should they use?

Accepted Answer

Azure Computer Vision - OCR. Azure Computer Vision's OCR (Optical Character Recognition) API is specifically designed to extract printed text from images, handling various fonts, sizes, and alphanumeric characters. This makes it the ideal choice for reading product labels to update inventory records, as it can process the diverse label formats commonly found in retail environments.

Answer

Azure Face Service

Answer

Azure Form Recognizer

Answer

Azure Video Indexer

Question 7

A bank is developing an AI system to automatically approve personal loans. To ensure the system does not discriminate against any group of applicants, which Microsoft responsible AI principle should the bank primarily focus on?

Accepted Answer

Fairness. Fairness is the correct principle because it directly addresses the need to prevent discrimination in AI systems, such as loan approval models. By focusing on fairness, the bank ensures that the model's predictions do not systematically disadvantage any group based on protected attributes like race, gender, or age, which is critical for ethical and legal compliance.

Answer

Accountability

Answer

Inclusiveness

Answer

Reliability and Safety

Question 8

A global e-commerce company is designing an AI-powered chatbot to assist customers. They want to ensure the chatbot can be used by people with diverse abilities, including those who use screen readers or speak different languages. Which Microsoft responsible AI principle is most directly related to this requirement?

Accepted Answer

Inclusiveness. The requirement to support screen readers and multiple languages directly aligns with Microsoft's responsible AI principle of inclusiveness, which aims to design AI systems that empower everyone, including people with disabilities and diverse linguistic backgrounds. In the context of a chatbot, inclusiveness ensures features like screen reader compatibility (via ARIA labels and semantic HTML) and multilingual natural language processing (NLP) models that can handle different languages and dialects, making the technology accessible to a broader audience.

Answer

Fairness

Answer

Reliability and Safety

Answer

Transparency

Question 9

A law firm needs to automatically categorize documents (e.g., 'contract', 'pleading', 'memo') and extract specific clauses such as 'indemnity' and 'confidentiality'. They have a large set of labeled examples for both tasks. Which combination of Azure AI Language features should they use?

Accepted Answer

Custom text classification and custom named entity recognition. The law firm needs to categorize documents (a text classification task) and extract specific clauses (a named entity recognition task). Custom text classification allows training a model on labeled examples to classify documents into categories like 'contract' or 'pleading', while custom named entity recognition (NER) can be trained to extract domain-specific entities such as 'indemnity' and 'confidentiality' clauses from the text. Azure AI Language supports both custom features, enabling the firm to build tailored models using their labeled dataset.

Answer

Prebuilt sentiment analysis and key phrase extraction

Answer

Question answering and conversation summarization

Answer

Language detection and translation

Question 10

What does 'confidence score' mean in Azure AI Custom Vision object detection results?

Accepted Answer

The model's certainty about a detection, used to set thresholds balancing false positives vs misses. In Azure AI Custom Vision, the confidence score is a numerical value (0 to 1) that represents the model's certainty that a detected object is correctly identified and localized. This score allows you to set a threshold to filter out low-certainty detections, balancing false positives (detections with low confidence) against misses (true objects that fall below the threshold). It is not a measure of training data composition, test accuracy, or human review.

Answer

The percentage of training images that contained this type of object

Answer

The accuracy of the model measured on the test dataset during training

Answer

A quality rating assigned by human reviewers to confirm the detection is correct

Question 11

What is the 'alignment problem' in AI safety and why is it significant?

Accepted Answer

The challenge of building AI systems that reliably pursue what humans actually intend rather than gaming the specification. The alignment problem refers to the fundamental challenge in AI safety where a system may optimize for a literal or mis-specified objective, leading to unintended or harmful behavior. For example, a reinforcement learning agent tasked with 'maximizing score' might find a way to exploit a bug in the simulation rather than learning the intended skill. This is significant because misaligned AI can cause real-world harm, especially as systems become more capable and autonomous.

Answer

Making AI models work consistently across different hardware platforms and cloud providers

Answer

Aligning AI model training data with current regulations and compliance requirements

Answer

Ensuring all team members agree on the objectives before beginning an AI project

Question 12

A language teacher uses Azure AI Language to automatically analyze hundreds of student essays. The teacher wants to identify the main topics discussed in each essay and also understand the overall sentiment (positive, negative, or neutral) expressed. Which two prebuilt Azure AI Language features should the teacher use together to accomplish this goal?

Accepted Answer

Key phrase extraction and Sentiment analysis. The teacher needs two features: one to identify main topics and one to analyze sentiment. Key phrase extraction extracts key phrases that represent the main topics, and sentiment analysis provides the overall sentiment. Option A is the only correct combination. Option D includes entity recognition, which identifies named entities like people or places, not the main topics discussed. Options B and C do not correctly pair a topic-identifying feature with sentiment analysis.

Answer

Entity recognition and Language detection

Answer

Text summarization and Key phrase extraction

Answer

Sentiment analysis and Entity recognition

Question 13

A hotel chain wants to analyze thousands of guest reviews to understand the overall tone of feedback (positive or negative) and to extract the most commonly mentioned features (e.g., 'room cleanliness', 'staff friendliness', 'breakfast'). Which two Azure AI Language features should they combine?

Accepted Answer

Sentiment analysis and key phrase extraction. The scenario requires two objectives: understanding the overall tone (positive/negative) and extracting commonly mentioned features. Sentiment analysis directly provides the tone. Key phrase extraction identifies important phrases like 'room cleanliness'. Therefore, the correct combination is sentiment analysis and key phrase extraction (Option A). Option C (key phrase extraction and entity linking) lacks sentiment analysis, so it does not fully address the requirement. Entity linking helps disambiguate entities but does not capture tone, making Option C incomplete.

Answer

Entity recognition and language detection

Answer

Key phrase extraction and entity linking

Answer

Text summarization and sentiment analysis

Question 14

A data scientist is training a model to classify customer reviews as positive, negative, or neutral. The dataset contains 10,000 reviews, but only 500 of them are negative. The data scientist wants to ensure the model performs well on the minority class (negative reviews). Which technique should the data scientist consider to address the class imbalance?

Accepted Answer

Use a resampling technique like SMOTE or random oversampling of the minority class. Resampling techniques like SMOTE (Synthetic Minority Oversampling Technique) or random oversampling directly address class imbalance by generating synthetic samples or duplicating existing samples from the minority class (negative reviews). This balances the training dataset, preventing the model from being biased toward the majority class (positive/neutral reviews) and improving recall for the minority class.

Answer

Increase the learning rate

Answer

Add more features to the model

Answer

Use L1 regularization (Lasso)

Question 15

What is 'Azure AI Custom Vision' and how does it differ from Azure AI Vision?

Accepted Answer

Azure AI Vision offers pre-built general models; Custom Vision lets you train models for your specific categories. Azure AI Vision provides pre-trained models for common computer vision tasks like object detection, OCR, and image analysis without requiring custom training data. Azure AI Custom Vision, on the other hand, allows you to upload your own labeled images and train a model to recognize specific categories or objects that are unique to your business scenario. This distinction makes B correct because it highlights the key difference: pre-built general models versus custom-trained models.

Answer

Azure AI Vision is for video; Custom Vision is for still images only

Answer

Custom Vision is more expensive because it uses more advanced AI algorithms

Answer

Azure AI Vision requires GPU compute; Custom Vision runs on CPU only

Question 16

A news agency needs to automatically process thousands of news articles and extract specific structured information: the publication date, the author's name, and the headline. None of these fields are standard predefined entities in Azure AI Language. Which Azure AI Language feature should they use to train a model to extract these custom entities?

Accepted Answer

Custom Named Entity Recognition (Custom NER). Custom Named Entity Recognition (Custom NER) is the correct choice because it allows you to train a model to extract domain-specific entities—such as publication date, author name, and headline—that are not part of Azure's predefined entity catalog. By providing labeled examples, Custom NER learns to identify these custom fields from unstructured text, enabling automated extraction from thousands of news articles.

Answer

Key phrase extraction

Answer

Sentiment analysis

Answer

Language detection

Question 17

What is a foundation model in the context of AI?

Accepted Answer

A large general-purpose AI model trained at scale that can be adapted to many downstream tasks. A foundation model is a large-scale, general-purpose AI model trained on vast and diverse datasets, enabling it to be adapted or fine-tuned for a wide range of downstream tasks such as text generation, translation, and image recognition. This definition aligns with option B, as foundation models like GPT-4 or BERT are designed for broad applicability rather than a single task.

Answer

A small specialized model optimized for a single specific task

Answer

The underlying hardware infrastructure for running AI workloads

Answer

A model that has been certified as ethically sound by regulators

Question 18

What is 'model explainability' using SHAP values in Azure Machine Learning?

Accepted Answer

Calculating each feature's contribution to a specific prediction to explain why the model made that decision. SHAP (SHapley Additive exPlanations) values are a game-theoretic approach that assigns each feature an importance value for a particular prediction. Option B is correct because SHAP values quantify the contribution of each input feature to the model's output, providing a local explanation for why a specific decision was made. This is distinct from global feature importance or model simplification.

Answer

Explaining the model's predictions using a simplified version of the model that is easier to interpret

Answer

Displaying the model's source code so users can verify what computations are performed

Answer

Testing the model on a separate evaluation dataset to report overall accuracy

Question 19

What is computer vision and give three real-world application examples.

Accepted Answer

Computer vision enables machines to understand visual data — used in autonomous driving, medical imaging, and retail automation. Computer vision is a field of AI that enables machines to interpret and make decisions based on visual data from the world, such as images and videos. The three examples given—autonomous driving (e.g., detecting pedestrians and lane markings), medical imaging (e.g., analyzing X-rays for tumors), and retail automation (e.g., self-checkout systems recognizing products)—are classic real-world applications that demonstrate the breadth of computer vision beyond simple text recognition.

Answer

Computer vision is limited to text recognition only; it cannot detect objects

Answer

Computer vision only works on satellite imagery for geographic analysis

Answer

Computer vision requires extremely expensive hardware unavailable in the cloud

Question 20

A manufacturing company uses overhead cameras on an assembly line to check that each part is present in the correct location on a circuit board. The system must not only confirm the part is there but also draw a box around each part to show its exact position. Which Azure Computer Vision capability should they use?

Accepted Answer

Object Detection. Object Detection is the correct capability because it not only identifies whether a specific object (like a circuit board part) is present in an image but also returns bounding box coordinates that indicate the exact location of each detected object. This meets the requirement to both confirm the part's presence and draw a box around it.

Answer

Optical Character Recognition (OCR)

Answer

Image Classification

Answer

Face Detection