Microsoft Practice Questions, Discussions & Exam Topics by our Authors
DRAG DROP - Your network contains an on-premises Active Directory domain named contoso.com. The domain contains a user named User1. You have an Azure subscription that is linked to an Azure Active Directory (Azure AD) tenant named contoso.com. The tenant contains an Azure Storage account named storage1. Storage1 contains an Azure file share named share1. Currently, the domain and the tenant are not integrated. You need to ensure that User1 can access share1 by using his domain...Author: Rahul · Last updated May 18, 2026 |
You have a dataset that contains information about taxi journeys that occurred during a given period. You need to train a model to predict t...When training a model to predict the fare of a taxi journey, it’s essential to choose features that have a direct relationship with the fare. Let's evaluate each option based on its relevance to predicting the fare. Option A: The number of taxi journeys in the dataset - Reasoning: The number of taxi journeys in the entire dataset refers to the count of journeys that occurred, but it doesn't provide specific information about the fare of an individual journey. - Rejection: While this number may provide insights into overall activity, it doesn't directly affect the fare of a single journey. It's not a relevant feature for predicting the fare of individual trips. Option B: The trip distance of individual taxi journeys - Reasoning: The trip distance is a crucial feature in predicting the fare because the longer the trip, the higher the fare is likely to be. Taxi fares often depend on distance traveled (and sometimes time spent in the cab). - Selected for Trip Distance: This is an important feature because it directly influences the fare. A longer journey typically results in a higher fare, so including trip distance as a feature would help train the model to make accurate predictions. Option C: The fare of individual taxi journeys - Reaso... Author: Madison · Last updated May 13, 2026 |
SIMULATION - You need to ensure that the rg1lod1234578n1 Azure Storage account is encrypted by using a key stored in the KeyVault12345678 Azure ...To ensure that the rg1lod1234578n1 Azure Storage account is encrypted using a key stored in KeyVault12345678 Azure Key Vault, the task involves configuring customer-managed keys (CMK) for encryption. This is the preferred method when you want to control the encryption key used by your Azure Storage account, instead of using Microsoft-managed keys. Key Factors: 1. Encryption in Azure Storage: By default, Azure Storage accounts are encrypted with Microsoft-managed keys. However, you can use customer-managed keys (CMK) for additional control over the encryption process. The CMK would be stored in Azure Key Vault, and you can configure the storage account to use this key for encryption. 2. Key Vault: The Key Vault must be in the same subscription as the Azure Storage account and should have the correct key (RSA or AES) stored and configured for encryption. 3. Azure Storage Encryption Settings: To enable customer-managed keys, you must configure the encryption settings of the Azure Storage account to use a key stored in Azure Key Vault. Explanation of Options: Option 1: Enable Azure Storage Encryption using a key from KeyVault12345678: - This is the correct option. You can configure the storage account to use a key from KeyVault12345678 for encryption by setting the customer-managed keys (CMK) option. This will ensure that the storage account is encrypted with the key stored in KeyVault12345678. - In the Azure portal, you would navigate to the Encryption section of the storage account settings and select Customer-Managed Keys, and then specify KeyVault12345678 as the key source. Once configured, all data in the storage account will be encrypted using that key. Option 2: Use... Author: Daniel · Last updated May 18, 2026 |
You have a web app named WebApp1. You create a web application firewall (WAF) policy named WAF1. You need to protec...To protect WebApp1 using WAF1, you need to integrate the Web Application Firewall (WAF) policy with the web application in the correct manner. WAF is typically used in conjunction with a reverse proxy or edge service that can handle HTTP(S) traffic, such as Azure Front Door or Azure Application Gateway. Here's a breakdown of the options: Key Factors to Consider: 1. Web Application Firewall (WAF) is used to protect web applications from common web attacks, such as SQL injection, cross-site scripting (XSS), etc. It needs to be placed in front of the web application to filter incoming HTTP(S) traffic. 2. Integration with Front-End Services: WAF must be deployed as part of an edge service like Azure Front Door or Azure Application Gateway to effectively filter traffic before it reaches the web app. 3. WebApp1 alone doesn’t provide native WAF protection; it requires an intermediary service like Azure Front Door to handle the web traffic and apply WAF policies. Review of Each Option: A) Deploy an Azure Front Door: - Explanation: Azure Front Door is a global, scalable entry point that offers WAF capabilities and can be used to secure web applications. You can configure the WAF1 policy on Azure Front Door to protect WebApp1. - Reasoning: This is the correct choice. Deploying Azure Front Door in front of WebApp1 allows you to associate the W... Author: Liam123 · Last updated May 18, 2026 |
You need to predict the sea level in meters for the next 10 years. Which type of machine learning s...To predict the sea level in meters for the next 10 years, the appropriate machine learning approach would be regression. Explanation: 1. Classification: - Classification is used when the target variable is categorical (discrete classes). For example, if we were predicting whether the sea level would rise or not (binary classification), or categorizing the sea level into specific bands (low, medium, high), classification would be a suitable approach. However, since we're predicting a continuous value (the exact sea level in meters), classification is not suitable. 2. Regression: - Regression is used when the target variable is continuous. In this case, sea level in meters is a continuous value, and we are interested in predicting this value over time. Regression models can capture trends, correlations, and patterns in historical data and use them to predict future values, making it the most suitable choice for predicting sea level changes. - Key factors in this case are that we're dealing with time-s... Author: Lucas · Last updated May 13, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Ea...Sure! Let’s go statement by statement and explain why the answer is Yes/No for AI-900. --- 1. Automated machine learning is the process of automating the time-consuming, iterative tasks of machine learning model development → Yes ✅ Explanation: AutoML automates repetitive and complex steps in ML, such as: Data preprocessing (cleaning and normalizing) Feature engineering (creating useful variables) Algorithm selection (testing multiple algorithms) Hyperparameter tuning (finding the best parameters) This reduces the manual effort required to build models. --- 2. Automated machine learning can automatically infer the training data from the use case provided → No ❌ Explanation: AutoML cannot select your dataset for you. You must provide the training dataset. AutoML automates what to do with the dataset... Author: Ming · Last updated May 13, 2026 |
You have an Azure subscription that contains an Azure SQL database named sql1. You plan to audit sql1. You need to configure the audit log destination. The solution must meet the following requirements: * Support querying events...To configure the audit log destination for your Azure SQL Database (sql1), let's analyze the options based on the requirements: Key Requirements: 1. Support querying events using Kusto Query Language (KQL): KQL is primarily used with Azure Log Analytics and Azure Monitor, which allows you to query logs for deeper analysis. The logs should be stored in a service that supports KQL. 2. Minimize administrative effort: This suggests a solution that requires less manual configuration or ongoing management. Review of Each Option: A) An Event Hub: - Explanation: Event Hubs is a service for receiving and managing large amounts of data, often used for real-time analytics and integration with other systems. - Rejected Reason: Although Event Hub is useful for streaming logs, it does not natively support querying events using KQL. You would need to set up additional infrastructure to store the logs in a service like Log Analytics to query them using KQL. This requires more administrative effort and does not directly meet the requirement of querying logs with KQL. B) A Storage Account: - Explanation: A storage account can be used as a destination for audit logs in Azure SQL Database. Logs can be stored in Blob Storage and accessed later for analysis. - Rejected Reason: While a storage account can store logs, it d... Author: ShadowWolf101 · Last updated May 18, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. A banking system that predicts whether a loan will be repaid is a...Let’s carefully analyze this. Scenario: > A banking system predicts whether a loan will be repaid. Key clue: The output is categorical: either “repaid” or “not repaid”. --- Options: A. Classification ✅ Classification predicts categories or classes. Example: spam vs. not spam, yes vs. no, repaid vs. not repaid. B. Regression ❌ Regression pred... Author: Ethan · Last updated May 13, 2026 |
DRAG DROP - You have an Azure subscription. You plan to create a storage account. You need to use customer-managed keys to encrypt the tables in the storage account. From Azure Cloud Shell, which three cmdlets should you run in sequence? To answer, move the approp...Author: Ava · Last updated May 18, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Ea...Here’s the Yes / No evaluation for your statements: 1. Labelling is the process of tagging training data with known values → Yes ✅ Labelling assigns the correct outputs (targets) to training examples. 2. You should evaluate a model by using the same data used to train the model → No ❌ Evaluation should ... Author: Oliver · Last updated May 13, 2026 |
HOTSPOT - You have an Azure subscription that contains the following resources: * An Azure key vault * An Azure SQL database named Database1 Two Azure App Service web apps named AppSrv1 and AppSrv2 that are configured to use system-assigned managed identities and access Database1 You need to implement an encryption solution for Database1 that meets the following requirements: * The data in a column named Discount in Database1 must be encrypted so that only AppSrv1 can decrypt the data. * AppSrv1 and AppSrv2 must be authorized by usi...Author: Grace · Last updated May 18, 2026 |
Which service should you use to extract text, key/value pairs, and table data automatically from sca...To extract text, key/value pairs, and table data automatically from scanned documents, the best option is Form Recognizer. Explanation: 1. Form Recognizer: - Form Recognizer is specifically designed for extracting structured data from documents such as forms and tables. It uses machine learning models to identify key-value pairs, text, and tables within scanned documents and images. It can handle a wide variety of document types, including invoices, receipts, and contracts, making it the most suitable option for automatically extracting text and structured data from scanned documents. - Key factors: Ability to process and extract text, key-value pairs, and tables from scanned documents and images. It is tailored for forms and documents, making it highly accurate and efficient for the task at hand. 2. Text Analytics: - Text Analytics is a service that primarily focuses on extracting insights from unstructured text, such as sentiment analysis, key phrase extraction, language detection, and named entity recognition. While it can be useful for processing plain text, it is not designed to extract structured data like tables or key-value pairs from scanned documents. - Rejection reason: It does not provide specific functionality for dealing with scanned or structured documents (like key-value pairs or tables) and focuses more on textual analysis rather than data extraction from images. 3. Language Understanding (LUIS): - LUIS (Language Understanding) is a natural ... Author: Grace · Last updated May 13, 2026 |
HOTSPOT - You have an Azure subscription that contains the storage accounts shown in the following table. You need to configure authorization access. Which authorization types can you use for each storage account? To answer, select t...Author: NightmareDragon2025 · Last updated May 18, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. The ability to extract subtotals and totals from a receip...✅ B. Form Recognizer Explanation: Form Recognizer is specifically designed to extract structured data from documents such as receipts, invoices, and forms. It can automatically identify and extract subtotals, totals, taxes, dates, and merchant details from receipts. Why the other options are incorrect: A. Custom Vis... Author: Aarav2020 · Last updated May 13, 2026 |
DRAG DROP - You have an Azure Storage account named storage1 and an Azure virtual machine named VM1. VM1 has a premium SSD managed disk. You need to enable Azure Disk Encryption for VM1. Which three actions should you perform in sequence? To answer, move the approp...Author: Vikram · Last updated May 18, 2026 |
You use Azure Machine Learning designer to publish an inference pipeline. Which two parameters should you use to access the web service? Each correct answer presents...To access a web service published from an inference pipeline in Azure Machine Learning Designer, the correct parameters to use are C) the authentication key and D) the REST endpoint. Explanation: 1. Authentication Key (C): - Authentication keys are required to authenticate and authorize access to the published web service. Without an authentication key, external clients cannot securely interact with the service. The key ensures that only authorized users or applications can call the service. - Key factors: Security and authentication are essential for protecting the service and its data. The authentication key grants access to the service. 2. REST Endpoint (D): - The REST endpoint is the URL where the web service can be accessed. This is the address used to send HTTP requests (such as POST or GET) to the service. Every Azure Machine Learning web service has a unique REST endpoint. - Key factors: The REST endpoint is the primary method for interacting with the service over the web. It allows external systems to send data to the model and get predictions back. Rejected options: 3. Model Name (A): - The model name is used for identifying the model when it is deployed or registered in the Azure Machine Learning workspace... Author: Sofia · Last updated May 13, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. From Azure Machine Learning designer, to deploy a real-time inference pipeline as a servi...Correct answer: C) Azure Kubernetes Service (AKS). Why this is correct for AI-900: In Azure Machine Learning designer, a real-time inference pipeline must be deployed as a web service. AKS is the standard and recommended production deployment option for real-time inference pipelines that will be consumed by others. AKS supports: High availability Auto-scaling Production workloads Why the other options are incorre... Author: Emma · Last updated May 13, 2026 |
SIMULATION - You need to enable Advanced Data Security for the SQLdb1 Azure SQL database. The solution must ensure that Azure Advanced Threat Protection (ATP) alerts are sent to [email protected]...To enable Advanced Data Security for SQLdb1 and ensure that Azure Advanced Threat Protection (ATP) alerts are sent to [email protected], you'll need to follow the proper steps in the Azure portal. Here’s an overview of the key actions and considerations: Key Factors: 1. Advanced Data Security: This is a feature in Azure SQL Database that provides additional security, including Advanced Threat Protection (ATP), which helps detect unusual and potentially harmful activities. 2. ATP Alerts: ATP alerts are part of the Advanced Data Security package, and to receive these alerts, you need to configure Alert Notifications to be sent to specific users, like [email protected]. 3. Actions in the Azure Portal: You need to enable Advanced Data Security and configure the notification settings to send alerts to the appropriate user. Steps in Azure Portal: 1. Enable Advanced Data Security on SQLdb1: - Navigate to the SQLdb1 instance in the Azure portal. - Under Security, select Advanced Data Security. - Turn on Advanced Threat Protection (ATP), which is part of Advanced Data Security. 2. Configure ATP Alert Notifications: - Once ATP is enabled, you need to set up Alert Policies under the Advanced Threat Protection settings. - In the Advanced Threat Protection settings, specify the email address [email protected] to receive the alerts. Review of Options: Option 1: Enable Advanced Data Security and configure email alerts - Explanation: This option aligns with the requirement. You will enable Advanced Data Security on SQLdb1 and configure ATP alerts to be sent to [email protected]. - Selected Reason: This option is the most straightforward solution that meets all the requirements — enabling Advanced Data Security and ensuring that alerts are sent to the correct email. Option 2: Enable Azure Security Center for SQLdb1 and configure alerts - Explanation: While Az... Author: Emma · Last updated May 18, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Predicting how many hours of overtime a delivery person will work based on...The correct answer is C) regression. Explanation of each option: A) Classification Classification is used when the output is a category or label, such as Yes/No, High/Medium/Low, or Spam/Not Spam. 👉 Example: Predicting whether a delivery person will work overtime or not. B) Clustering Clustering is used to group data without predefined lab... Author: Maya · Last updated May 13, 2026 |
SIMULATION - You need to configure a weekly backup of an Azure SQL database named Homepage. The backup must be retained for eight we...To configure a weekly backup for an Azure SQL Database named Homepage and retain it for eight weeks, you need to leverage Azure’s built-in backup and retention capabilities. Azure SQL Database provides automatic backups that can be configured for long-term retention (LTR) for your needs. Key Factors: 1. Weekly Backup: Azure SQL Database supports automated backups. By default, Azure retains backups for 7 to 35 days, depending on the service tier. However, you can configure long-term retention (LTR) for backups beyond the default retention period. 2. Retention for 8 Weeks: To meet the retention requirement of 8 weeks, LTR is the most suitable option because it allows you to specify the duration for which you want to retain your backups. Review of Each Option: A) Use the built-in automated backup with long-term retention (LTR) - Explanation: Long-Term Retention (LTR) is a feature of Azure SQL Database that allows you to retain backups for an extended period, such as 8 weeks, 1 year, or even up to 10 years. You can configure weekly backups and specify retention policies (e.g., retaining weekly backups for 8 weeks). - Reasoning: This is the most appropriate solution. LTR allows you to define a weekly backup retention policy, and you can set it to retain backups for 8 weeks as required. - How to Implement: In the Azure portal, navigate to the SQL database, then configure long-term retention settings, and specify that you want weekly backups to be retained for 8 weeks. B) Use the Azure SQL Database Point-in-Time Restore feature - Explanation: Point-in-Time Restore allows you to restore a database to a specific time within the retention period (7-35 days, depending on the service tier). It is not a proactive backup strategy and does not provide the capa... Author: SolarFalcon11 · Last updated May 18, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Ea...The correct answer is: ✅ D) Yes, Yes, No Explanation: 1. Azure Machine Learning designer provides a drag-and-drop visual canvas to build, test, and deploy machine learning models → Yes Azure ML Designer is a visual, drag-and-drop interface used to build, train, evaluate, and deploy ML pipelines without writing code. 2. Azure Machine Learning designer enables you to save your pr... Author: Aria · Last updated May 13, 2026 |
SIMULATION - You need to ensure that when administrators deploy resources by using an Azure Resource Manager template, the deployment can access secrets in an Azure key va...To ensure that when administrators deploy resources using an Azure Resource Manager (ARM) template, the deployment can access secrets in an Azure Key Vault named `KV12345678`, you would typically need to grant the necessary permissions to allow access to secrets in the Key Vault during the deployment process. This can be done in a few different ways in Azure. Below are the potential options and reasoning behind each. Options: 1. Managed Identity for the ARM Template Deployment (System-assigned or User-assigned Managed Identity) - Reasoning: The deployment itself can use a managed identity (either system-assigned or user-assigned) to authenticate to Azure resources securely, including accessing secrets in Azure Key Vault. The managed identity can be granted the appropriate role (e.g., `Key Vault Secrets User`) to allow access to the secrets. This approach is considered best practice as it is a secure, identity-based authentication method that avoids using credentials directly. - Scenario: This is commonly used when you want to ensure the deployment can access resources without requiring credentials in the deployment script, which is more secure. 2. Service Principal Authentication (Using a Service Principal with a Secret or Certificate) - Reasoning: A service principal can be created to authenticate the deployment process, and then it can be granted access to the Key Vault secrets. This option is less secure than using managed identities because it relies on storing secrets or certificates for authentication, which could potentially be compromised if not handled securely. - Scenario: This option might be used in older scenarios where managed identities are not available, or if there is a requirement to use a specific service principal that has more defined permissions outside the context of managed identi... Author: RadiantPhoenixX · Last updated May 18, 2026 |
HOTSPOT - You have the following dataset. You plan to use the dataset to train a model that will predict the house price categories of houses. What are Household Income and House Price Category? To answer, select the ap...Here’s a clear explanation for this question: We are looking at a dataset: | Household Income | Postal Code | House Price Category | | ---------------- | ----------- | -------------------- | | 20,000 | 55555 | Low | | 23,000 | 20541 | Middle | | 30,000 | 87960 | High | In machine learning terminology: 1. Feature (Input) → The variables that help the model make predictions... Author: Mia · Last updated May 13, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Azure Machine Learning designer lets you cr...The correct answer is: ✅ A) adding and connecting modules on a visual canvas. Explanation: Azure Machine Learning Designer is a drag-and-drop, no-code visual interface for building machine learning pipelines. You add modules (like data input, data prep, train model, score model) and connect them to define the workflow visually. Why not the others? B) automatically performing comm... Author: BlazingPhoenix22 · Last updated May 13, 2026 |
HOTSPOT - You have an Azure subscription that contains the storage accounts shown in the following table. You enable Azure Defender for Storage. Which storage services of storage5 are monitored by Azure Defender for Storage, and which storage accounts are protected by Azure Defender for Sto...Author: Manish · Last updated May 18, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Hot Area: Automated machine leaming provides you with the ability to include custom Python scripts in a training pipeline? Automated machine learning implements machine learning solutions without the ne...Let’s go carefully, step by step, for AI-900 context: --- 1. Include custom Python scripts in a training pipeline? AutoML itself is designed for no-code automated model training. You cannot directly include custom Python scripts in the no-code AutoML interface. Custom scripts are only possible via Python SDK, which is an advanced feature beyond basic AutoML. ✅ Answer: No --- 2. Implements ML solutions without programming experience? Yes. This is the main purpose of AutoML: it automates algorithm selection,... Author: Aditya · Last updated May 13, 2026 |
You have an Azure subscription that contains as Azure key vault and an Azure Storage account. The key vault contains customer-managed keys. The storage account is configured to use the customer-managed keys stored in the key vault. You plan to store data in Azure by using the following services: * Azure Files * Azure Blob storage * Azure Table storage * Azure Queue storage Which two se...To determine which Azure services support encryption with customer-managed keys (CMK) stored in Azure Key Vault, let's break down each service in the context of encryption: Options: 1. Azure Files - Reasoning: Azure Files supports encryption using customer-managed keys (CMK) stored in Azure Key Vault. When you use Azure Files with an Azure Storage account, you can configure the storage account to use a customer-managed key (instead of the default Microsoft-managed keys) for encryption at rest. This is a common use case where organizations need to control the encryption keys themselves. - Scenario: Azure Files is often used for shared file storage in the cloud, and it’s useful to ensure that data is encrypted with keys controlled by the customer. 2. Azure Blob Storage - Reasoning: Azure Blob Storage also supports encryption using customer-managed keys stored in Azure Key Vault. By setting up a storage account with CMK, you can encrypt your blob data with your own keys. This is the most commonly used service for storing unstructured data in Azure, such as images, videos, and backups, and supports encryption using CMK. - Scenario: Azure Blob Storage is widely used for large-scale object storage, and the ability to use customer-managed keys is often required for compliance and security reasons. 3. Azure Table Storage - Reasoning: Azure Table Storage does not support encryption wit... Author: IceDragon2023 · Last updated May 18, 2026 |
A medical research project uses a large anonymized dataset of brain scan images that are categorized into predefined brain haemorrhage types. You need to use machine learning to support early detection of the different brain haemorrhage types in th...This is an example of C) classification machine learning. Explanation: 1. Classification: - Classification is used when the goal is to categorize input data into predefined classes or labels. In this case, the dataset contains brain scan images that are already categorized into predefined brain haemorrhage types. The machine learning model's task is to classify new images into one of these types before they are reviewed by a person. - Key factors: The task involves labeling the images into specific categories (types of brain haemorrhage). Classification models are specifically designed for this purpose, as they can learn from labeled data to classify new, unseen instances. 2. Clustering: - Clustering is an unsupervised learning technique where the model groups similar data points together based on their features. In clustering, there are no predefined labels or categories, and the goal is to identify patterns or groupings within the data. - Rejection reason: Clustering would not be appropriate here because the data is already labeled into specific categories (brain haemorrhage types)... Author: Isabella · Last updated May 13, 2026 |
SIMULATION - You need to ensure that connections through an Azure Application Gateway named Homepage-AGW are inspected for malicious requests. To complete this task, sign...To ensure that connections through an Azure Application Gateway named Homepage-AGW are inspected for malicious requests, you would need to configure Web Application Firewall (WAF) on the Azure Application Gateway. WAF is designed to provide centralized protection to your web applications from common threats such as SQL injection, cross-site scripting (XSS), and other OWASP top 10 vulnerabilities. Options: 1. Enable Web Application Firewall (WAF) on Application Gateway - Reasoning: Web Application Firewall (WAF) is a feature of the Azure Application Gateway that helps protect web applications from common threats and vulnerabilities. WAF analyzes HTTP/HTTPS traffic for patterns of malicious activity and applies rules to block or alert on these attempts. It is the most suitable option for inspecting malicious requests as it is specifically designed for security inspection. - Scenario: This option should be used when you need to monitor and block malicious requests, ensuring that your web application is protected from common threats. This is ideal for securing web traffic handled by the Application Gateway. 2. Enable SSL termination on Application Gateway - Reasoning: SSL termination allows the Application Gateway to decrypt incoming SSL traffic, but it doesn't inspect for malicious requests. While it facilitates traffic inspection at the application level by decrypting traffic, it doesn't inherently provide security against threats like SQL injection or XSS, which is the core requirement of the task. - ... Author: James · Last updated May 18, 2026 |
When training a model, why should you randomly split the rows into separate subsets?The correct reason to randomly split the rows into separate subsets is C) to test the model by using data that was not used to train the model. Explanation: 1. To test the model by using data that was not used to train the model (C): - Key reason: When training a machine learning model, it’s crucial to have separate data for training and testing. The purpose of testing the model is to evaluate how well it generalizes to unseen data, not just how well it fits the training data. If we use the same data for both training and testing, the model may overfit, meaning it performs well on the training data but poorly on new, unseen data. - Key factors: Randomly splitting the data ensures that the model is tested on data that it hasn't seen before, providing a more accurate assessment of its performance and helping to prevent overfitting. 2. To train the model twice to attain better accuracy (A): - This is not a valid reason for splitting data into subsets. Training a model multiple times on the same data does not necessarily improve its accuracy. The purpose of splitting the data is to create a separate testing set to evaluate model performance, not to train the model multiple times. -... Author: RadiantJaguar56 · Last updated May 13, 2026 |
SIMULATION - You need to create a web app named Intranet12345678 and enable users to authenticate to the web app by using Azure Active Directory (...To enable users to authenticate to a web app named Intranet12345678 using Azure Active Directory (Azure AD), you need to integrate Azure AD authentication into the web app. This can be done by enabling Azure AD authentication during the app's configuration. Below are the available options for enabling this authentication: Options: 1. Enable Azure Active Directory Authentication (Azure AD authentication) for the Web App - Reasoning: Azure AD authentication is specifically designed to allow users to authenticate using their Azure Active Directory credentials. By selecting this option, you can integrate Azure AD as the identity provider for your web app. This is the most direct and appropriate solution to enable user authentication via Azure AD. - Scenario: This is the correct option when you want users to sign in using their Azure AD credentials, which is often required in enterprise scenarios for securing internal web applications. 2. Use Social Accounts (Facebook, Google, etc.) for Authentication - Reasoning: This option allows users to authenticate via social media accounts (e.g., Facebook, Google) instead of Azure AD. It is generally used when you want to allow public or third-party users to log in, but it is not suitable for enterprise scenarios where users must authenticate via Azure AD. - Scenario: Use this if you want to provide external users or customers access to the web app, but it's not appropriate for internal users who must authenticate using Azure AD. 3. Use a Custom Auth... Author: Isabella1 · Last updated May 18, 2026 |
You are evaluating whether to use a basic workspace or an enterprise workspace in Azure Machine Learning. What are two tasks that require an enterprise workspace? Each correct answer ...To evaluate the tasks that require an Enterprise Workspace in Azure Machine Learning, let's break down each option with respect to their requirements: A) Use a graphical user interface (GUI) to run automated machine learning experiments. - Enterprise Workspace is designed for larger scale and organizational use, including the automation of machine learning workflows. This often requires an enterprise setup for advanced features like automated ML (AutoML), which might include more data and resource management for scaling. - Explanation: Running automated machine learning experiments typically benefits from the organizational management and scaling capabilities of the enterprise setup. Hence, this option likely requires an enterprise workspace. B) Create a compute instance to use as a workstation. - This can be done in both a Basic Workspace and an Enterprise Workspace. Azure Machine Learning allows the creation of compute instances for development purposes, and this feature is available in both workspace types. - Explanation: Basic workspaces are sufficient for this task because it is not specifically tied to enterprise-scale resources or governance. C) Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer. ... Author: Emma · Last updated May 13, 2026 |
DRAG DROP - You have an Azure subscription that contains a Microsoft SQL server named Server1 and an Azure key vault named vault1. Server1 hosts a database named DB1. Vault1 contains an encryption key named key1. You need to ensure that you can enable Transparent Data Encryption (TDE) on DB1 by using key1. Which four actions should you perform in...Author: Noah · Last updated May 18, 2026 |
You need to predict the income range of a given customer by using the following dataset. Which two fields should you use as features? Each correct answer presents...To predict the income range of a given customer, we need to select features that have a meaningful relationship with income. Let's analyze each option: A) Education Level - Explanation: Education level can be a good predictor of income, as there is often a correlation between a person's level of education and their earning potential. For example, people with higher levels of education may tend to have higher incomes. - Reasoning: This is a useful feature for predicting income because education can influence career opportunities and salary expectations. B) Last Name - Explanation: The last name typically does not provide any meaningful information about the customer’s income. It is a categorical variable that does not have a direct correlation with income. - Reasoning: This is not a relevant feature for predicting income, as it does not offer any predictive power about the income range. C) Age - Explanation: Age can be a significant predictor of income, as income levels often vary with experience and career stage. For example, younger individuals might earn less due to being e... Author: MysticJaguar44 · Last updated May 13, 2026 |
You are building a tool that will process images from retail stores and identify the products of competitors. The solution will use a custom ...To process images from retail stores and identify products of competitors using a custom model, let's evaluate the available Azure Cognitive Services options: A) Custom Vision - Explanation: Custom Vision is designed specifically for custom image classification and object detection. It allows you to train a custom model using your own labeled image data. This service is ideal for identifying specific objects, such as products in retail store images. You can train a model to recognize competitor products with your own dataset, making it highly suitable for the scenario described. - Reasoning: Custom Vision is the best fit because it allows you to create custom models to classify and detect specific items (in this case, competitor products) from images. This directly aligns with the need to process retail images and identify specific products. B) Form Recognizer - Explanation: Form Recognizer is designed to extract data from forms, documents, and receipts. It is tailored for reading structured information from documents, such as invoices, purchase orders, or receipts, rather than for identifying objects or products in images. - Reasoning: This service is not suitable for identifying products in images, as its use case is focused on extracting structured data from forms, not recognizing objects or items in general images. C... Author: Maya · Last updated May 13, 2026 |
HOTSPOT - You have an Azure subscription that contains an Azure key vault named KeyVault1 and the virtual machines shown in the following table. You set the Key Vault access policy to Enable access to Azure Disk Encryption for volume encryption. KeyVault1 is configured as shown in the following exhibit. For each of the ...Author: Henry · Last updated May 18, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Organizing documents into groups based on similarities of the text contained in the documents is an example of clustering ? Grouping similar patients based on symptoms and diagnostic test results is an example of...1. Organizing documents into groups based on text similarity You don’t know the groups ahead of time; the algorithm finds patterns and clusters similar documents together. This is classic clustering (unsupervised learning). 2. Grouping similar patients based on symptoms and tests You are grouping patients without predefined labels, just bas... Author: Lucas · Last updated May 13, 2026 |
You have an Azure subscription that contains an Azure SQL database named DB1 in the East US Azure region. You create the storage accounts shown in the following table. You plan to enable audit...When you enable auditing for an Azure SQL Database (DB1), the auditing logs can be sent to Azure Storage or Log Analytics. For Azure Storage, the destination must meet certain requirements, such as being in the same region or a compatible region for auditing data. Let's review the options based on the table and logic for selecting the storage accounts that are compatible for auditing: Factors to Consider: 1. Same Region: The storage account must be in the same region as the Azure SQL Database (East US) for auditing. This is important because cross-region data transfers for auditing logs could result in additional latency and possible failures in log delivery. 2. General-purpose storage account (v2): The storage account must be a general-purpose v2 account or specifically support auditing for Azure SQL Database. 3. Azure Storage Account Types: Depending on the type of storage account (e.g., general-purpose v2, premium, etc.), not all types may be suitable for auditing logs. The auditing logs typically need to be stored in a standard storage account. Analysis of Options: Storage Accounts: - Storage1: A general-purpose v2 storage account located in the same region (East US) as DB1. - Storag... Author: VenomousSerpent42 · Last updated May 18, 2026 |
HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Ea...Let’s carefully analyze each statement about the validation set in machine learning: --- 1. "A validation set includes the set of input examples that will be used to train a model?" No. The training set is used to train the model. The validation set is separate; it is used to tune hyperparameters and evaluate model performance during training, not to train the model. ✅ Answer: No --- 2. "A validation set can be used to determine how well a model predicts labels?" Yes. The validation set is used to assess model performance, typically ... Author: Ming88 · Last updated May 13, 2026 |
DRAG DROP - You have an Azure subscription that contains an Azure SQL database named SQLDB1. SQLDB1 contains the columns shown in the following table. For the Email and Birthday columns, you implement dynamic data masking by using the default masking function. Which value will the users see in each column? To answer, drag the appropriate values to the correct columns. Each value may be used once, m...Author: Aria · Last updated May 18, 2026 |
What are two metrics that you can use to evaluate a regression model? Each correct answer presents a complete solution...In evaluating a regression model, the following two metrics are commonly used: A) Coefficient of determination (R²): - Explanation: R² is a measure of how well the regression model explains the variance in the dependent variable. It ranges from 0 to 1, where 1 indicates that the model explains all the variance, and 0 indicates that the model does not explain any variance. R² is commonly used for regression models as it gives an indication of the goodness-of-fit. - Use case: R² is best used when you want to measure how well your model fits the data, making it appropriate for regression analysis. - Rejection reason for others: - B) F1 score: This is used in classification problems to balance precision and recall. It's not suitable for regression models. - D) Area under the curve (AUC): AUC is primarily used in binary classification problems to evaluate the performance of a classifier. It doesn’t apply to regression models. - E) Balanced accuracy: Balanced accuracy is a metric for classification tasks, espe... Author: Liam · Last updated May 13, 2026 |
HOTSPOT - You have a hybrid Azure Active Directory (Azure AD) tenant named contoso.com that contains a user named User1 and the servers shown in the following table. The tenant is linked to an Azure subscription that contains a storage account named storage1. The storage1 account contains a file share named share1. User1 is assigned the Storage File Data SMB Share Contributor role for storage1. The Security protocol settings for the file shares of storage1 are co...Author: Julian · Last updated May 18, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Predicting how many vehicles will travel across a bridg...Let’s analyze carefully: The task: Predict how many vehicles will travel across a bridge. Key point: The output is a numeric value (number of vehicles). --- Options: A) Classification → Used when predicting categories or labels (e.g., “High income” vs. “Low income”). ❌ B) Clustering → Used for grouping data without labels, finding patt... Author: Kunal · Last updated May 13, 2026 |
You have an on-premises network and an Azure subscription. You have the Microsoft SQL Server instances shown in the following table. You plan to implement Microsoft Defender for SQ...To determine which SQL Server instances will be protected by Microsoft Defender for SQL, let's analyze each option and the conditions under which Microsoft Defender for SQL works. Key Factors to Consider: - Microsoft Defender for SQL can protect SQL Server instances hosted in Azure and on-premises instances with proper configuration. - Defender for SQL can be enabled on: 1. Azure SQL databases and SQL managed instances directly within the Azure environment. 2. On-premises SQL Server instances through a connection to Azure Defender via Azure Arc, which enables management of on-premises resources in Azure. Analysis of the Options: - Option A: sql1 and sql2 only - This option would suggest that only sql1 and sql2 are protected, but we need to understand the specifics of these instances. If sql1 and sql2 are both on-premises and there is no mention of Azure Arc configuration for these instances, they may not be protected by Microsoft Defender for SQL. - Rejected if sql1 and sql2 are on-premises and not connected to Azure via Azure Arc. - Option B: sql1, sql2, and sql3 only - sql1 and sql2 could... Author: James · Last updated May 18, 2026 |
DRAG DROP - You need to use Azure Machine Learning designer to build a model that will predict automobile prices. Which type of modules should you use to complete the model? To answer, drag the appropriate modules to the correct locations. Each module may be used once, more than once, or not at all. You may n...Let’s carefully go step by step: Step 1: After raw dataset After loading raw data, it’s common to select which columns to use. Module: `Select Columns in Dataset` ✅ --- Step 2: Clean missing values Already included: `Clean Missing Data / Remove missing value rows` ✅ --- Step 3: Split data Before training, we need to split into training and testing sets. Module: `Split Data` ✅ --- ... Author: Sofia2021 · Last updated May 13, 2026 |
HOTSPOT - You have a Microsoft Sentinel deployment. You need to connect a third-party security solution to the deployment. The third-party solution will send Common Event Format (CEF)-formatted messages. What should you include in the solution? To...Author: Ava · Last updated May 18, 2026 |
Which type of machine learning should you use to identify groups of people who have similar purchasi...To identify groups of people who have similar purchasing habits, the most suitable type of machine learning would be: C) Clustering: - Explanation: Clustering is an unsupervised learning technique used to group similar data points together based on features such as purchasing habits, without prior knowledge of the categories. The goal is to identify clusters or groups within the data that exhibit similar patterns. Clustering algorithms such as K-means, DBSCAN, or hierarchical clustering are ideal for grouping people based on their purchasing behavior. - Use case: This is commonly used in customer segmentation, where you want to identify groups of people who share similar purchasing behaviors or characteristics for targeted marketing or personalized services. Rejection of other options: - A) Classification: Classification is a sup... Author: William · Last updated May 13, 2026 |
You have an Azure subscription that contains an Azure SQL Database logic server named SQL1 and an Azure virtual machine named VM1. VM1 uses a private IP address only. The Firewall and virtual networks settings for SQL1 are shown in the following exhibit. You need ...To ensure that VM1 can connect to the Azure SQL Database logic server SQL1 using the principle of least privilege, we need to carefully consider the configurations and constraints. Let's break down the options and explain why one might be selected over the others. Key Factors: - Firewall and Virtual Network settings: SQL1 has firewall settings that restrict access to certain IP addresses. VM1 is using a private IP address, so it must be on the same virtual network or connected to the virtual network of SQL1 to connect successfully. - Principle of least privilege: We want to minimize the changes and grant the least amount of access required to allow connectivity. Analyzing the Options: A) Set Connection Policy to Proxy - Proxy mode allows SQL client traffic to go through the proxy layer, which might be necessary for connections from clients outside Azure or in specific network configurations. - However, this doesn't address the core issue here, which is ensuring VM1 on a private IP can access SQL1. - Rejected because it's not specifically focused on solving the issue of access for VM1. B) Set Allow Azure services and resources to access this server to Yes - This option allows Azure services to access SQL1, which would include services like Azure VMs or other Azure resources, irrespective of their IP address. - Since VM1 is using a private IP address, this may not be nece... Author: Lucas Carter · Last updated May 18, 2026 |
HOTSPOT - To complete the sentence, select the appropriate option in the answer area. _______________models can be used to...Correct answer: C) Regression Explanation: Regression models are designed to predict numerical (continuous) values. Since the sale price of an auctioned item is a number (for example, $150 or $2,500), regression is the appropriate model. Classification predicts cate... Author: Layla · Last updated May 13, 2026 |
You have an Azure Active Directory (Azure AD) tenant that contains a group named Group1. You need to ensure that the members of Group1 sign i...To ensure that the members of Group1 sign in using passwordless authentication, let's evaluate the options available and determine the most appropriate action based on the requirements. Key Factors: - Passwordless Authentication: This involves methods where users can authenticate without using traditional passwords, typically through methods like Microsoft Authenticator app, Windows Hello for Business, or FIDO2 security keys. - Group1 members: The goal is to ensure members of this group can sign in passwordlessly, so the solution must focus on enforcing passwordless sign-in methods. Analysis of Options: A) Configure the sign-in risk policy - Sign-in risk policies are part of Azure AD Identity Protection. They assess the risk of a sign-in attempt (e.g., based on unusual sign-in activity) and enforce actions like requiring multi-factor authentication (MFA) if a high risk is detected. - However, this policy does not specifically enforce passwordless authentication; it is more about managing the risk of the sign-in, not the authentication method itself. - Rejected because it's not directly related to enforcing passwordless authentication but rather focusing on risk assessment. B) Create a Conditional Access policy - Conditional Access policies are used to enforce certain conditions for user sign-ins, such as requiring MFA, restricting access based on location, or enforcing certain authentication methods. - While Conditional Access can enforce passwordless authentication as part of its rules (e.g., requiring users to use Microsoft Authenticator), it is generally a br... Author: Max · Last updated May 18, 2026 |