AI-300 Certification Practice Question #2

Question

A team trains an MLflow model that scores customer churn risk. The model will be consumed by different downstream systems.
One system requests predictions synchronously during customer interactions.
Another system submits files containing millions of records for scheduled scoring.
You need to deploy the model by using managed inference options that match each usage pattern.
Which option should you use for each usage pattern? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Accepted Answer

The two usage patterns map cleanly to Azure ML's two managed inference modes. A system that needs predictions *synchronously during customer interactions* requires a **real-time (online) endpoint**, which returns results over HTTP in low latency. A system that *submits files of millions of records for scheduled scoring* is the textbook **batch endpoint** case — asynchronous, parallelized over compute, no low-latency requirement. The remaining options are training/registry artifacts or raw compute, not inference deployment targets.

More AI-300 practice questions