Databricks Certified Machine Learning Professional — Question 78

A machine learning engineer needs to select a deployment strategy for a new machine learning application. The machine learning application requires central prediction computation and exceedingly fast results, but only a handful of predictions need to be computed at a time.

Which deployment strategy can be used to meet these requirements?

Answer options

• A. Streaming
• B. Real-time
• C. Batch
• D. Edge/on-device

Correct answer: B

Explanation

The correct answer is B, Real-time, as it is designed for scenarios requiring immediate predictions with low latency. Option A, Streaming, is more suited for continuous data flows rather than isolated predictions. Option C, Batch, processes large volumes of data at once, which does not align with the need for speed and low volume in this case. Option D, Edge/on-device, focuses on local processing, which may not support the centralized computation requirement.