FirstTry

Objective 1.1

PMLE

Developing ML models using BigQuery ML or AutoML

Objective 1.1 sits in Architecting low-code AI solutions, which carries 13% of the ML Engineer exam. The questions below are original, written from the official objective title above, and each explanation cites the Google Cloud page it rests on.

Objective title verbatim from the official objectives. Google Cloud exam page ↗

A worked example

Shown solved, with the whole explanation open: this is what every question here carries.

1-1Architecting low-code AI solutions

An analyst reruns a model build every night under one fixed model name and wants the previous model swapped out rather than an error returned. Which statement form does that?

CREATE MODEL mymodelA name collision here raises an error instead.
CREATE MODEL IF NOT EXISTS mymodelThis form trains nothing once the name is taken.
CREATE OR REPLACE MODEL mymodelCorrect · your answerCorrect. The nightly rebuild overwrites in place.
ALTER MODEL mymodel SET OPTIONSChanging options on a stored model does not retrain it.

Correct.

Concept

A data definition language has to declare what happens when the name is already taken, and there are only three sensible answers: refuse, skip quietly, or overwrite. Picking one is picking the collision behaviour a repeatable job needs.

Why C

CREATE MODEL returns an error if the model name exists. CREATE MODEL IF NOT EXISTS trains only when the model is absent from the dataset. CREATE OR REPLACE MODEL trains and replaces the model of the same name.

Source

CREATE MODEL Creates and trains a new model in the specified dataset. If the model name exists, CREATE MODEL returns an error. CREATE MODEL IF NOT EXISTS Creates and trains a new model only if the model does not exist in the specified dataset. CREATE OR REPLACE MODEL Creates and trains a model and replaces an existing model with the same name in the specified dataset.

The CREATE MODEL statement, BigQuery ML reference, checked August 2026
#gcp#bigquery-ml#sql#model-lifecycle

Now you: objective 1.1 questions

No account needed. The explanation opens when you answer.

Sample question 1 of 3

1-1Architecting low-code AI solutions

An engineer tries to create a model whose name matches a table that already sits in the same dataset. What does the naming rule for models say about that?

Sample question 2 of 3

1-1Architecting low-code AI solutions

A team adds a preprocessing clause that emits three engineered columns, while the query underneath it returns twelve columns. Which columns feed training?

Sample question 3 of 3

1-1Architecting low-code AI solutions

At inference time a team asks which of the original columns must be supplied for a model that was built with a preprocessing clause. What has to be passed?

Full ML Engineer question bank coming

We’re writing the complete bank from the official objectives right now. Leave your email and we’ll tell you when it ships, nothing else, ever.

Read the sources

These are the official pages the questions above cite. Reading them is studying the objective from the primary source, which is what the explanations point you toward anyway.