2.3 Define, Train, Evaluate, and Use ML Models ASSOCIATE-DATA-PRACTITIONER Practice Questions (Page 3)

Questions 11–15

1. 11foundation · easy

   In a BigQuery ML CREATE MODEL statement, which clause is used to specify the model type (e.g., linear_reg, logistic_reg)?

   • AAS SELECT
   • BOPTIONS
   • CMODEL_TYPE
   • DTRAINING
   Reveal Solution Discussion Select an answer first
2. 12application · medium

   A data analyst wants to use a pretrained Google LLM to summarize product descriptions stored in BigQuery. They have already created a remote connection. What is the next step to invoke the LLM from BigQuery?

   • AExport the data to Cloud Storage and use the Vertex AI API.
   • BUse ML.PREDICT directly on the remote connection.
   • CTrain a custom model in BigQuery ML on the product descriptions.
   • DCreate a BigQuery model that references the LLM endpoint, then use ML.GENERATE_TEXT in a query.
   Reveal Solution Discussion Select an answer first
4. 13foundation · easy

   When training a BigQuery ML model, what does the CREATE MODEL statement do?

   • AIt registers a model already trained in Vertex AI
   • BIt only creates an empty model shell that must be trained separately
   • CIt evaluates the model and returns performance metrics
   • DIt creates and trains the model in a single SQL statement
   Reveal Solution Discussion Select an answer first
5. 14foundation · easy

   What does the ML.EVALUATE function return?

   • AThe model's training loss at each iteration
   • BA set of model performance metrics
   • CThe SQL query used to train the model
   • DThe predicted values for the input data
   Reveal Solution Discussion Select an answer first
6. 15foundation · easy

   Which BigQuery ML function is used to generate predictions from a trained model on new data?

   • AML.TRAIN
   • BML.PREDICT
   • CML.CREATE
   • DML.EVALUATE
   Reveal Solution Discussion Select an answer first