Databricks-ML-Assoc Model Deployment Practice Question
An ML engineer deployed a model to a Databricks Model Serving endpoint and enabled inference tables. After a week, the team notices that some requests returned HTTP 200 but the corresponding rows in the inference table show null prediction values. They need to diagnose why predictions are missing for those requests. Which explanation is most consistent with this symptom?
⚠ Common exam trap
The trap here is assuming a successful HTTP status guarantees a fully populated inference table row, when response-shape mismatches can leave the prediction column null.
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
✓
The model returned a response shape that the serving layer could not map to the prediction column.
Inference tables capture request and response payloads for each served request, and the serving layer derives the prediction column from the model's response structure. When a model returns output in a format the logging layer does not recognize as a prediction, the request still succeeds with HTTP 200 but the logged prediction is null. Sampling, autoscaling, and read permissions produce different symptoms such as missing rows or errors, not present rows with null predictions.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The endpoint's autoscaling reduced replicas, causing dropped responses.
Why it's wrong here
Autoscaling adjusts replica count based on load but does not cause successful responses to be logged with null predictions. If a replica were unavailable, the request would fail or be retried rather than return HTTP 200 with missing output. Inference table entries are written from completed requests, so a scaling event alone would not produce null prediction values for successful calls.
- ✓
The model returned a response shape that the serving layer could not map to the prediction column.
Why this is correct
Inference tables log request and response payloads, and the serving layer extracts predictions based on the expected response structure. If the model returns a dict or array that does not match the expected prediction field, the endpoint can still return HTTP 200 while the logged prediction column is null. This mismatch between the model's output shape and the logging schema is a common cause of missing predictions in inference tables.
- ✗
The endpoint's service principal lacked SELECT permission on the inference table.
Why it's wrong here
Missing SELECT permission would prevent reading the table, not writing null values into it. Permission problems on the write path would typically surface as an error when the endpoint tries to append logs, or as missing rows, rather than as present rows with null predictions. Since the team can query the table and see rows, read permissions are not the issue.
- ✗
The inference table was configured with a sampling fraction that excluded those rows.
Why it's wrong here
Sampling affects which requests are logged at all, not the content of logged rows. A row excluded by sampling would be absent from the table entirely, not present with a null prediction. Since the symptom is rows that exist but have null predictions, sampling configuration cannot explain the missing values and would instead manifest as fewer overall rows.
About these practice questions
One of 319 original Databricks-ML-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.