2.3 Define, Train, Evaluate, and Use ML Models ASSOCIATE-DATA-PRACTITIONER Practice Questions (Page 1)

Questions 1–5

1. 1foundation · easy

   For a time-series model trained in BigQuery ML, which function is used to generate forecasts?

   • AML.EVALUATE
   • BML.FORECAST
   • CML.FORECASTING
   • DML.PREDICT
   Reveal Solution Discussion Select an answer first
2. 2foundation · easy

   A data analyst needs to build a binary classification model to predict customer churn. The training data is already stored in BigQuery, and the analyst wants to create and train the model using only SQL, without exporting data to a separate environment. Which Google Cloud service is most appropriate for this task?

   • AVertex AI AutoML
   • BVertex AI Custom Training
   • CCloud Dataflow
   • DBigQuery ML
   Reveal Solution Discussion Select an answer first
4. 3foundation · easy

   What is the primary purpose of the Model Registry in Google Cloud?

   • ATo store training datasets
   • BTo execute SQL queries
   • CTo manage and version machine learning models
   • DTo monitor model training jobs
   Reveal Solution Discussion Select an answer first
5. 4application · medium

   A data science team is starting a new ML project to predict customer churn. They have collected historical data and are about to begin the project. According to a standard ML project lifecycle, what should they do immediately after data collection?

   • APrepare and split the data into training, validation, and test sets.
   • BDeploy the model to production to get real-time predictions.
   • CTrain an initial model on the raw data to establish a baseline.
   • DEvaluate the model using ML.EVALUATE on the full dataset.
   Reveal Solution Discussion Select an answer first
6. 5expert · hard

   A data team wants to use a pretrained Google LLM to classify customer support tickets into categories. The tickets are stored in BigQuery. They have created a remote connection and a model that references the LLM. However, when they run a query with ML.GENERATE_TEXT, they get an error that the model is not found. What is the most likely cause?

   • AThe model was created in a different project or region than the query is running in.
   • BThe remote connection is not authorized to access the LLM endpoint.
   • CThe LLM endpoint is not available in the chosen region.
   • DThe tickets table does not have a text column.
   Reveal Solution Discussion Select an answer first