AIF-C01 practice questions 11–20

1. Question 11 · 417 in bank

   A company wants to use a large language model (LLM) to generate concise, feature-specific descriptions for the company’s products. Which prompt engineering technique meets these requirements?

   • ACreate one prompt that covers all products. Edit the responses to make the responses more specific, concise, and tailored to each product.
   • BCreate prompts for each product category that highlight the key features. Include the desired output format and length for each prompt response.
   • CInclude a diverse range of product features in each prompt to generate creative and unique descriptions.
   • DProvide detailed, product-specific prompts to ensure precise and customized descriptions.

   Show answer

   Answer: B

   Explanation

   This approach ensures that the prompts are tailored to specific product categories, guiding the LLM to generate concise, feature-specific descriptions. Including the desired output format and length further refines the model’s responses, making them consistent and aligned with the company’s requirements.

   Source: Adapted from community discussion — chdaphne

   Next question

2. Question 12 · 417 in bank

   A company is developing an ML model to predict customer churn. The model performs well on the training dataset but does not accurately predict churn for new data. Which solution will resolve this issue?

   • ADecrease the regularization parameter to increase model complexity.
   • BIncrease the regularization parameter to decrease model complexity.
   • CAdd more features to the input data.
   • DTrain the model for more epochs.

   Show answer

   Answer: B

   Explanation

   Increase the regularization parameter to decrease model complexity. Increasing the regularization parameter helps prevent overfitting by penalizing more complex models, encouraging the model to generalize better to new data. Would you like more detailed information on how to implement this change or any other aspect of model tuning?

   Source: Adapted from community discussion — 26b8fe1

   Next question

3. Question 13 · 417 in bank

   A company wants to build an ML model by using Amazon SageMaker. The company needs to share and manage variables for model development across multiple teams. Which SageMaker feature meets these requirements?

   • AAmazon SageMaker Feature Store
   • BAmazon SageMaker Data Wrangler
   • CAmazon SageMaker Clarify
   • DAmazon SageMaker Model Cards

   Show answer

   Answer: A

   Explanation

   Amazon SageMaker Feature Store ensures all teams have access to a centralized store of features, improving consistency and collaboration in ML workflows.

   Source: Adapted from community discussion — galliaj

   References

   • AWS documentation

   Next question

4. Question 14 · 417 in bank

   A company is implementing intelligent agents to provide conversational search experiences for its customers. The company needs a database service that will support storage and queries of embeddings from a generative AI model as vectors in the database. Which AWS service will meet these requirements?

   • AAmazon Athena
   • BAmazon Aurora PostgreSQL
   • CAmazon Redshift
   • DAmazon EMR

   Show answer

   Answer: B

   Next question

5. Question 15 · 417 in bank

   A financial institution is building an AI solution to make loan approval decisions by using a foundation model (FM). For security and audit purposes, the company needs the AI solution's decisions to be explainable. Which factor relates to the explainability of the AI solution's decisions?

   • AModel complexity
   • BTraining time
   • CNumber of hyperparameters
   • DDeployment time

   Show answer

   Answer: A

   Explanation

   Model complexity is the most important factor when considering the explainability of the AI solution's decisions, as simpler models with fewer parameters and layers are typically easier to explain and interpret.

   Source: Adapted from community discussion — aws_Tamilan

   Next question

6. Question 16 · 417 in bank

   A pharmaceutical company wants to analyze user reviews of new medications and provide a concise overview for each medication. Which solution meets these requirements?

   • ACreate a time-series forecasting model to analyze the medication reviews by using Amazon Personalize.
   • BCreate medication review summaries by using Amazon Bedrock large language models (LLMs).
   • CCreate a classification model that categorizes medications into different groups by using Amazon SageMaker.
   • DCreate medication review summaries by using Amazon Rekognition.

   Show answer

   Answer: B

   Next question

7. Question 17 · 417 in bank

   A company wants to build a lead prioritization application for its employees to contact potential customers. The application must give employees the ability to view and adjust the weights assigned to different variables in the model based on domain knowledge and expertise. Which ML model type meets these requirements?

   • ALogistic regression model
   • BDeep learning model built on principal components
   • CK-nearest neighbors (k-NN) model
   • DNeural network

   Show answer

   Answer: A

   Explanation

   A: Logistic regression model Explanation: A logistic regression model is interpretable and allows direct adjustment of the weights assigned to different variables (features). This aligns with the requirement for employees to view and modify the weights based on their domain knowledge and expertise. Logistic regression provides a clear relationship between input features and output predictions, making it ideal for use cases that demand transparency and control.

   Source: Adapted from community discussion — Moon

   Next question

8. Question 18 · 417 in bank

   HOTSPOT - A company wants to build an ML application. Select and order the correct steps from the following list to develop a well-architected ML workload. Each step should be selected one time.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   

   Next question

9. Question 19 · 417 in bank

   Which strategy will determine if a foundation model (FM) effectively meets business objectives?

   • AEvaluate the model's performance on benchmark datasets.
   • BAnalyze the model's architecture and hyperparameters.
   • CAssess the model's alignment with specific use cases.
   • DMeasure the computational resources required for model deployment.

   Show answer

   Answer: C

   Explanation

   C: Assess the model's alignment with specific use cases. Explanation: To determine if a foundation model (FM) effectively meets business objectives, it is crucial to evaluate how well the model aligns with the specific use cases and objectives of the business. This involves testing the model's performance on real-world tasks and ensuring that it addresses the desired outcomes, such as accuracy, relevance, and user satisfaction, in the context of the business problem. Why not the other options? A: Evaluate the model's performance on benchmark datasets: While benchmarking provides useful insights into the model's capabilities, it does not guarantee alignment with business-specific needs or objectives.

   Source: Adapted from community discussion — Moon

   Next question

10. Question 20 · 417 in bank

    A company needs to train an ML model to classify images of different types of animals. The company has a large dataset of labeled images and will not label more data. Which type of learning should the company use to train the model?

    • ASupervised learning
    • BUnsupervised learning
    • CReinforcement learning
    • DActive learning

    Show answer

    Answer: A

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AIF-C01 practice, question 11. 417 questions available.