Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Associate Data Practitioner practice bank has 1,156 more like it. Try 10 free: instant score, no account.
A data analyst has trained a classification model named customer_churn_model using BigQuery ML to predict customer attrition. The analyst now needs to generate batch predictions on a new dataset of current subscribers stored in a table named active_customers and output the predicted labels alongside customer identifiers for a marketing campaign.
Which BigQuery ML function should the analyst use to execute these predictions?
ML.EVALUATE is a BigQuery ML evaluation function designed to assess the performance and statistical accuracy of a trained machine learning model against a labeled evaluation dataset.
ML.EVALUATE outputs aggregate statistical performance metrics—such as precision, recall, accuracy, F1-score, log loss, and ROC AUC for classification models—rather than generating individual row-level predictions for customer scoring.predicted_ or pass through individual record identifiers.The scenario stated: "The data analyst wants to calculate the ROC AUC, precision, and recall metrics of the trained churn model against a holdout test dataset to validate its accuracy prior to deployment."
ML.TRAIN is not a valid SQL syntax or function in BigQuery ML. In BigQuery ML, model training is initiated using the Data Definition Language (DDL) command CREATE OR REPLACE MODEL ... AS SELECT ... rather than an ML.TRAIN function.
ML.TRAIN in BigQuery SQL syntax.ML.PREDICT.CREATE MODEL project.dataset.model_name OPTIONS(model_type='LOGISTIC_REG') AS SELECT ....ML. prefix are used for inference, model inspection, evaluation, feature preprocessing, or model weights extraction (e.g., ML.PREDICT, ML.EVALUATE, ML.ROC_CURVE, ML.CONFUSION_MATRIX, ML.FEATURE_INFO).A function named ML.TRAIN existed and the requirement was specifically to initiate model parameter fitting on historical training data rather than performing inference.
ML.PREDICT is the standard BigQuery ML function used to generate predictions, classifications, or cluster assignments using a previously trained machine learning model. It allows data practitioners to run batch inference directly inside BigQuery using standard SQL syntax without exporting data or managing external prediction microservices.
ML.PREDICT takes the trained model name (customer_churn_model) and an input table or subquery (active_customers) to generate predicted labels for each record in parallel.ML.PREDICT includes all original input columns alongside new prediction columns (such as predicted_ and predicted__probs), making it easy to filter, aggregate, or join directly with downstream marketing and reporting tables.customer_id) from the input data alongside prediction outputs.ML.PREDICT is specifically designed for supervised and unsupervised batch inference on tabular datasets. It minimizes operational complexity and latency by executing predictive scoring directly where the data resides.
ML.FORECAST is a specialized time series forecasting function in BigQuery ML used specifically with time series models, such as ARIMA_PLUS or ARIMA_PLUS_XREG.
ML.FORECAST cannot be used with classification models like logistic regression, boosted trees, or random forests; it operates exclusively on univariate and multivariate time series forecasting models.ML.FORECAST specifies forecast horizons and confidence intervals rather than scoring a tabular feature matrix of active users.ARIMA_PLUS time series models.forecast_value, standard_error, confidence_level, and prediction interval bounds (prediction_interval_lower_bound, prediction_interval_upper_bound).The scenario stated: "The analyst has trained an ARIMA_PLUS model on historical daily subscription cancellations and needs to forecast total subscriber churn counts for the next 60 days with an 80% confidence interval."
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated