An analyst team that knows SQL needs a churn model from data already in BigQuery, as fast as possible. What fits?
Why C is the answer
BigQuery ML
BigQuery ML trains models with SQL where the data already lives.
In detail
- BigQuery ML builds models in SQL, where the data already is.
- Evaluation and prediction are SQL too.
Use case
An illustrative scenario, not a real incident.
Analysts train a churn model with CREATE MODEL in BigQuery, with no data export and no new tools.
See it in different ways
flowchart TD
A{"Where does the team work?"} -->|"SQL in BigQuery"| B["BigQuery ML"]
A -->|"No code, managed training"| C["Agent Platform AutoML"]
A -->|"Common task, no training needed"| D["Pre-built APIs: Document AI, Vision, Translate"]stateDiagram-v2 [*] --> Task Task --> PrebuiltApi: a common task Task --> BigQueryMl: data in BigQuery, SQL team Task --> AutoML: custom model, no code Task --> CustomTraining: your own code
flowchart LR S0["CREATE MODEL"] --> S1["ML.EVALUATE"] --> S2["ML.PREDICT"]
Key point: BigQuery ML trains models with SQL.
Why the other options are wrong
- A. A hand-built PyTorch model
- A hand-built model takes far longer.
- B. Fine-tuning a Gemini model
- Gemini fine-tuning is not for churn prediction on tables.
- D. A custom TensorFlow job on GKE
- A custom job takes far longer.