Databricks-ML-Assoc Model Deployment Practice Question
A team is standing up a real-time Databricks Model Serving endpoint for a fraud model. Requests will carry several numeric features, and the team wants the endpoint to reject malformed payloads with a clear client error rather than silently scoring them, and to avoid cold-start latency during business hours. Which two actions should the team take? (Choose two.)
⚠ Common exam trap
The trap here is treating scale-to-zero as a pure win, when it directly conflicts with a requirement to avoid cold starts.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Configure a non-zero minimum number of serving instances so replicas stay warm.
Declaring an MLflow model signature gives the endpoint a schema contract so invalid payloads are refused before scoring, and holding a minimum instance count above zero keeps replicas loaded so requests are not delayed by provisioning. Together these satisfy both the fail-fast validation goal and the warm-capacity latency goal, whereas scale-to-zero, inference tables and registry choice affect cost or governance only.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Configure a non-zero minimum number of serving instances so replicas stay warm.
Why this is correct
Keeping a minimum instance count above zero holds provisioned, model-loaded replicas ready at all times. Requests arriving during business hours are handled immediately rather than waiting for a container to start and load artifacts, which removes the cold-start delay. This is the standard control for latency-sensitive endpoints that must respond predictably even after periods of low traffic.
- ✗
Set the endpoint's scale-to-zero behaviour so idle capacity is released between requests.
Why it's wrong here
Scale-to-zero reduces cost by releasing capacity when traffic stops, but the first request afterwards must wait for a replica to provision and load the model. That reintroduces exactly the cold-start latency the team wants to eliminate during business hours. It is a sound cost optimization for intermittent workloads, yet it works against the stated latency goal here.
- ✗
Register the model in the workspace Model Registry instead of Unity Catalog.
Why it's wrong here
The choice of registry governs governance, access control and lineage, not request validation or replica warmth. Moving the model into the workspace registry would not cause malformed payloads to be rejected, nor would it reduce cold-start latency. It simply changes where the model is governed and can even weaken the centralized permission model the team may already rely on.
- ✗
Enable inference tables to persist the request and response payloads.
Why it's wrong here
Inference tables capture request and response data into a Delta table for monitoring, debugging and drift analysis. They are valuable for observability, but they neither validate payload schemas nor keep replicas warm, so they do not address the two requirements in the stem. Enabling them is worthwhile for governance, yet it is orthogonal to input rejection and cold-start avoidance.
- ✓
Log the model with an MLflow model signature that declares the input schema and types.
Why this is correct
The model signature records the expected input columns and their types in the MLmodel metadata. Model Serving uses that contract to validate incoming payloads, so a request missing a required column or supplying a string where a double is expected is rejected instead of being coerced or scored incorrectly. This directly delivers the requirement that malformed payloads fail fast with a client-facing error.
About these practice questions
This Databricks-ML-Assoc question is part of Courseiva's 319-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-ML-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-ML-Assoc exam.