Describe Core Machine Learning Concepts AI-900 Practice Questions (Page 2)

Questions 6–10

1. 6foundation · easy

   In a machine learning dataset for predicting house prices, which of the following would be considered a feature?

   • AThe accuracy of the trained model
   • BThe number of bedrooms in each house
   • CThe unique identifier for each house listing
   • DThe actual sale price of each house
   Reveal Solution Discussion Select an answer first
2. 7expert · hard

   A team is developing a model to predict insurance claim severity. They have a dataset of 500,000 claims. The team plans to use the validation set to tune hyperparameters and compare models. After tuning, they want an unbiased estimate of final model performance. Which approach best satisfies this need?

   • ASplit the data into training, validation, and test sets; use validation for tuning and test for final evaluation
   • BTrain on the validation set and evaluate on the training set
   • CUse the validation set for tuning and then report its performance as the final estimate
   • DUse the training set for tuning and the validation set for final evaluation
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   A data scientist is preparing a dataset to train a model that classifies support tickets by priority. The dataset contains 10,000 labeled tickets. The scientist wants to evaluate how well the model generalizes to unseen tickets before deploying it. What is the primary purpose of holding out a portion of the data as a validation dataset?

   • ATo ensure the model memorizes the training examples exactly
   • BTo increase the size of the training dataset
   • CTo assess model performance on data not used during training
   • DTo replace the need for feature engineering
   Reveal Solution Discussion Select an answer first
5. 9foundation · easy

   Which statement correctly defines a feature in a machine learning dataset?

   • AA feature is a collection of labeled examples used to train the model.
   • BA feature is the output value that the model is trained to predict.
   • CA feature is a subset of data used to evaluate the trained model.
   • DA feature is an input variable that describes an attribute of the data.
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   In a supervised machine learning dataset for classifying emails as spam or not spam, what is the label?

   • AThe words in the email subject line
   • BThe time the email was received
   • CThe sender's email address
   • DThe category 'spam' or 'not spam' assigned to each email
   Reveal Solution Discussion Select an answer first