cert
cert-1
cert-2

Pass Databricks Certified Machine Learning Professional Exam in First Attempt Guaranteed!

Get 100% Latest Exam Questions, Accurate & Verified Answers to Pass the Actual Exam!
30 Days Free Updates, Instant Download!

cert-5
cert-6
Certified Machine Learning Professional Exam - Verified By Experts
Certified Machine Learning Professional Premium File

Certified Machine Learning Professional Premium File

$69.99
$76.99
  • Premium File 216 Questions & Answers. Last Update: Nov 12, 2026

Whats Included:

  • Latest Questions
  • 100% Accurate Answers
  • Fast Exam Updates
 
$76.99
$69.99
accept 12 downloads in the last 7 days
block-screenshots
Databricks Certified Machine Learning Professional Practice Test 14

Question 130

Review this production model incident: A fraud-feature drift monitor crosses its threshold but the alert has no assigned recipient and no incident ownership. Which mitigation resolves the defect rather than concealing it?

  1. Use a supported snapshot data profile for the governed table and its quality metrics.
  2. Configure a documented threshold with the responsible on-call team and a tested delivery route.
  3. Configure model-identity-aware inference monitoring with version-specific comparisons.
  4. Compute comparable version-specific performance trends and retain traffic-share context.

Explanation

Correct Answer

B:

This corrects the relevant failure boundary instead of merely hiding the symptom. Configure a documented threshold with the responsible on-call team and a tested delivery route. The issue matters because material drift remains unaddressed because nobody receives the notification.

Incorrect Answers

A:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: An analyst wants to inspect today’s static customer table for missing values and profile changes but chooses an inference monitor requiring model IDs and predictions. The relevant corrective action here is configure a documented threshold with the responsible on-call team and a tested delivery route.

C:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: An inference profile groups two active model versions into one aggregate and hides a regression introduced by the new release. The relevant corrective action here is configure a documented threshold with the responsible on-call team and a tested delivery route.

D:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A scoring endpoint quietly moves from model v7 to v8 during a rollout but an inference trend aggregates both versions in one error curve. The relevant corrective action here is configure a documented threshold with the responsible on-call team and a tested delivery route.

Question 131

Review this production model incident: A serving endpoint appears healthy but nobody records model version, request identifier or prediction value, so a drift incident cannot be reconstructed. What evidence would best distinguish the actual fault from neighboring ML concerns?

  1. Compare segment filters, join population and sampling criteria for both sides of the statistic.
  2. Compare historical baselines, current seasonal patterns and change approvals for the existing threshold.
  3. Inspect timestamp type, event cadence and intended daily windows before choosing the monitor.
  4. Inspect inference-record completeness for request, model version, inputs, outputs and timestamps.

Explanation

Correct Answer

D:

This is the most discriminating check for the observed symptoms. Inspect inference-record completeness for request, model version, inputs, outputs and timestamps. The underlying technical issue is that observability starts with traceable, appropriately governed prediction logging before statistical analysis.

Incorrect Answers

A:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A customer-risk monitoring job compares an unfiltered current high-risk segment to an all-customer historical baseline and interprets the difference as temporal drift. For the stated incident, the decisive observation is inspect inference-record completeness for request, model version, inputs, outputs and timestamps.

B:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A production alert threshold is hard-coded against last year's baseline, but seasonal traffic has shifted and the owner never reviewed the threshold. For the stated incident, the decisive observation is inspect inference-record completeness for request, model version, inputs, outputs and timestamps.

C:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A fleet sensor table records measurement timestamps and analysts need daily drift trends; a snapshot-only profile erases the time dimension. For the stated incident, the decisive observation is inspect inference-record completeness for request, model version, inputs, outputs and timestamps.

Question 132

Consider the following fictional Databricks production case: A continuous-delivery job deploys a notebook change through a bundle but skips validation of referenced experiment paths and job permissions. Which observation most directly tests the suspected failure boundary?

  1. Examine bundle validation results, actual resource permissions and downstream job execution traces.
  2. Inspect job ownership, compute policy and identity access after a simulated employee offboarding.
  3. Review per-team compute usage, job queuing and capacity constraints during overlapping workloads.
  4. Audit workspace bindings, job identities and catalog permissions for development workloads.

Explanation

Correct Answer

A:

This is the most discriminating check for the observed symptoms. Examine bundle validation results, actual resource permissions and downstream job execution traces. The underlying technical issue is that infrastructure/configuration definitions need predeployment validation and an integration check, not mere successful YAML parsing.

Incorrect Answers

B:

That diagnostic evidence is directed at a different environment architectures situation: A distributed retraining workflow uses ephemeral personal compute and fails when the original engineer's account is disabled. For the stated incident, the decisive observation is examine bundle validation results, actual resource permissions and downstream job execution traces.

C:

That diagnostic evidence is directed at a different environment architectures situation: A production deployment scales to 30 teams but all jobs share one compute pool with no capacity limits or cost attribution. For the stated incident, the decisive observation is examine bundle validation results, actual resource permissions and downstream job execution traces.

D:

That diagnostic evidence is directed at a different environment architectures situation: A company operates development and production models in one workspace under the same broad service account and frequently overwrites production tables during experiments. For the stated incident, the decisive observation is examine bundle validation results, actual resource permissions and downstream job execution traces.

Question 133

A production ML review contains this situation: A text pipeline repeatedly fits a Tokenizer stage even though tokenization simply converts strings into token arrays without learning a model. Which diagnostic check provides the strongest direct evidence?

  1. Compare saved preprocessing stage metadata and feature vector order across the two deployed artifacts.
  2. Inspect the stage class API and whether fitting produces any data-dependent parameters.
  3. Inspect class prevalence, the confusion matrix, minority recall and false-negative cost rather than headline accuracy.
  4. Inspect DataFrame physical operations and memory spikes at each Python collection boundary.

Explanation

Correct Answer

B:

This is the most discriminating check for the observed symptoms. Inspect the stage class API and whether fitting produces any data-dependent parameters. The underlying technical issue is that tokenizer is a Transformer and applies transform directly without a separate learned fit step.

Incorrect Answers

A:

That diagnostic evidence is directed at a different using spark ml situation: A batch scoring service loads a classifier version from last month while using today's new feature indexer, silently changing categorical positions. For the stated incident, the decisive observation is inspect the stage class API and whether fitting produces any data-dependent parameters.

C:

That diagnostic evidence is directed at a different using spark ml situation: A fraud detector predicts the majority no-fraud class for 99.4% of cases and advertises 99.4% accuracy while missing most positives. For the stated incident, the decisive observation is inspect the stage class API and whether fitting produces any data-dependent parameters.

D:

That diagnostic evidence is directed at a different using spark ml situation: An insurer already stores its risk features as a large Spark DataFrame but exports them into Python lists before every vector transformation and repeatedly hits out-of-memory errors. For the stated incident, the decisive observation is inspect the stage class API and whether fitting produces any data-dependent parameters.

Question 134

Review this production model incident: A team switches a SparkML training stage to Ray without verifying that its chosen estimator supports Ray's distributed fit contracts. Which mitigation resolves the defect rather than concealing it?

  1. Normalize per-group output columns and types before returning them to Spark.
  2. Use supported data parallelism with appropriately batched examples and convergence checks.
  3. Pin shared validation protocol and data snapshot for the compared Optuna trials.
  4. Retain SparkML for its supported distributed estimator or migrate to a validated Ray-compatible training algorithm.

Explanation

Correct Answer

D:

This corrects the relevant failure boundary instead of merely hiding the symptom. Retain SparkML for its supported distributed estimator or migrate to a validated Ray-compatible training algorithm. The issue matters because the rewritten job runs only on one worker or fails during model serialization.

Incorrect Answers

A:

That corrective action is directed at a different scaling and tuning situation: A per-city pandas UDF returns different prediction schemas for cities with absent categories, causing a distributed aggregation failure. The relevant corrective action here is retain SparkML for its supported distributed estimator or migrate to a validated Ray-compatible training algorithm.

B:

That corrective action is directed at a different scaling and tuning situation: A tabular classifier fits comfortably on one GPU and 100 million independent examples are available, but a team proposes splitting the small model's layers across hosts. The relevant corrective action here is retain SparkML for its supported distributed estimator or migrate to a validated Ray-compatible training algorithm.

C:

That corrective action is directed at a different scaling and tuning situation: A hyperparameter team compares two Optuna studies with different train/validation splits and chooses the lower loss as though both metrics were directly comparable. The relevant corrective action here is retain SparkML for its supported distributed estimator or migrate to a validated Ray-compatible training algorithm.

Question 135

The engineering team encounters the following issue: A sensor classifier silently reuses features from a year-old device after months without readings, despite a maximum allowed lookback of seven days. Which technical principle most directly explains the root of the issue?

  1. Streaming derived features should deduplicate at a stable business-event key before non-idempotent aggregation.
  2. Shared feature logic changes should be versioned and regression-tested across all consuming models.
  3. Temporal feature joins may need an explicit bounded lookback so stale records are not mistaken for current observations.
  4. Online feature lookup keys must be stable and uniquely identify the intended entity.

Explanation

Correct Answer

C:

The technical constraint is specific to the reported failure. Temporal feature joins may need an explicit bounded lookback so stale records are not mistaken for current observations. To test it, compare last available reading age with each prediction cutoff and its permitted freshness window.

Incorrect Answers

A:

That underlying principle is directed at a different advanced feature store concepts situation: A real-time feature job updates user purchase totals without checking whether upstream transaction events are delivered twice. The current incident instead turns on temporal feature joins may need an explicit bounded lookback so stale records are not mistaken for current observations.

B:

That underlying principle is directed at a different advanced feature store concepts situation: A team updates a shared on-demand feature function without version control and unexpectedly changes both batch retraining and online serving behavior. The current incident instead turns on temporal feature joins may need an explicit bounded lookback so stale records are not mistaken for current observations.

D:

That underlying principle is directed at a different advanced feature store concepts situation: A low-latency feature table uses external customer names as lookup keys; names change and are not unique. The current incident instead turns on temporal feature joins may need an explicit bounded lookback so stale records are not mistaken for current observations.

Question 136

Consider the following fictional Databricks production case: A drift alert fires but its message contains only the word anomaly without dataset, model version or baseline window. Which result is the strongest acceptance criterion after remediation?

  1. Precision and recall populate only for complete labeled cohorts, while unlabeled drift remains separately reported.
  2. An injected 5xx serving fault triggers an availability alert while the drift metric remains independently interpretable.
  3. A test alert identifies the precise asset, time window, threshold and metric that caused it.
  4. A controlled miscalibrated fixture shows a confidence-bin discrepancy while a calibrated control does not.

Explanation

Correct Answer

C:

This verification measures the required result rather than just process liveness. A test alert identifies the precise asset, time window, threshold and metric that caused it. It confirms whether the targeted action succeeded: include governed dataset/model identifiers, metric values and comparison periods in the alert payload.

Incorrect Answers

A:

That acceptance test is directed at a different drift detection and lakehouse monitoring situation: A model's inference table records output probabilities but omits ground-truth labels, yet reviewers expect immediate precision and recall metrics. Here the actual success criterion is a test alert identifies the precise asset, time window, threshold and metric that caused it.

B:

That acceptance test is directed at a different drift detection and lakehouse monitoring situation: An endpoint's error rate spikes while data profiles look normal, and responders attempt to retrain the model instead of checking serving infrastructure. Here the actual success criterion is a test alert identifies the precise asset, time window, threshold and metric that caused it.

D:

That acceptance test is directed at a different drift detection and lakehouse monitoring situation: A binary model's average predicted probability remains 0.4, but outcomes show that 0.8 predictions are now correct only half the time. Here the actual success criterion is a test alert identifies the precise asset, time window, threshold and metric that caused it.

Question 137

The engineering team encounters the following issue: A regulated analytics team uploads full customer identifiers inside MLflow model artifacts during troubleshooting. Which experiment most directly demonstrates a successful fix?

  1. A time-bounded replay produces understood feature differences and acceptable model performance.
  2. A scan of new run artifacts finds only approved fields while reproducing the required diagnostic behavior.
  3. Each worker's fit results appear under its own child run without overwritten artifacts.
  4. An experiment query retrieves one parent with all expected child trials and their distinct metrics.

Explanation

Correct Answer

B:

This verification measures the required result rather than just process liveness. A scan of new run artifacts finds only approved fields while reproducing the required diagnostic behavior. It confirms whether the targeted action succeeded: replace identifiers with synthetic or aggregated diagnostic evidence and restrict artifact access appropriately.

Incorrect Answers

A:

That acceptance test is directed at a different advanced mlflow usage situation: A deployed custom model fetches latest feature values during serving while offline evaluation used event-time snapshots without checking the difference. Here the actual success criterion is a scan of new run artifacts finds only approved fields while reproducing the required diagnostic behavior.

C:

That acceptance test is directed at a different advanced mlflow usage situation: A training orchestrator starts parallel child fits but all workers accidentally log into one active MLflow run and overwrite each other's metrics. Here the actual success criterion is a scan of new run artifacts finds only approved fields while reproducing the required diagnostic behavior.

D:

That acceptance test is directed at a different advanced mlflow usage situation: An experiment tunes 40 candidates but logs each trial as an unrelated root MLflow run, so reviewers cannot reconstruct which search produced a winner. Here the actual success criterion is a scan of new run artifacts finds only approved fields while reproducing the required diagnostic behavior.

Question 138

Review this production model incident: A team logs a custom Python model that imports a package installed only in the author's notebook, and the serving endpoint fails when loading the artifact. Which failure risk follows most closely from the unresolved behavior?

  1. A trained model works locally but cannot initialize outside the developer's session.
  2. The apparent best F1 cannot be reproduced because its hyperparameters were never captured.
  3. The deployed artifact cannot be tied to the training configuration that earned the winning metric.
  4. Important diagnostic evidence is absent from model review despite a reported scalar score.

Explanation

Correct Answer

A:

This consequence follows from the specific unresolved condition. A trained model works locally but cannot initialize outside the developer's session. The causal constraint is: Custom MLflow model packaging must include declared compatible dependencies for the independent serving environment.

Incorrect Answers

B:

That direct consequence is directed at a different advanced mlflow usage situation: A training notebook reports F1 for several models but only logs the final model's parameters in MLflow, leaving metrics and hyperparameters disconnected. The more immediate risk here is a trained model works locally but cannot initialize outside the developer's session.

C:

That direct consequence is directed at a different advanced mlflow usage situation: A data scientist selects the lowest validation loss from nested runs but reports only the parent run ID as the model-producing run. The more immediate risk here is a trained model works locally but cannot initialize outside the developer's session.

D:

That direct consequence is directed at a different advanced mlflow usage situation: An ML engineer logs a calibration plot as a string metric, then downstream reviewers cannot inspect the visualization or its input version. The more immediate risk here is a trained model works locally but cannot initialize outside the developer's session.

Question 139

Review this production model incident: An ML project stores test files directly in each production notebook and execution of a deployed notebook inadvertently reruns expensive tests. Which mitigation resolves the defect rather than concealing it?

  1. Use deterministic mapping order and assert category-to-index values in notebook tests.
  2. Add an environment-level integration test for table, model and serving input/output contracts.
  3. Keep reusable logic and tests in separate versioned units with explicit CI test stages.
  4. Build an end-to-end integration fixture that verifies schemas, versions and prediction outputs across stages.

Explanation

Correct Answer

C:

This corrects the relevant failure boundary instead of merely hiding the symptom. Keep reusable logic and tests in separate versioned units with explicit CI test stages. The issue matters because production jobs waste resources or mutate test artifacts during business scoring.

Incorrect Answers

A:

That corrective action is directed at a different validation testing situation: A notebook's label encoder produces a different category order depending on an unordered Python set, but tests assert only output length. The relevant corrective action here is keep reusable logic and tests in separate versioned units with explicit CI test stages.

B:

That corrective action is directed at a different validation testing situation: A team unit-tests each model component independently but its feature table and serving endpoint disagree on column names. The relevant corrective action here is keep reusable logic and tests in separate versioned units with explicit CI test stages.

D:

That corrective action is directed at a different validation testing situation: A churn feature job succeeds and a classifier achieves acceptable F1, but the deployed endpoint returns HTTP 400 because request column names differ. The relevant corrective action here is keep reusable logic and tests in separate versioned units with explicit CI test stages.

Question 140

Review this production model incident: An engineer logs a customer-specific API token inside the pickled PythonModel object before registering it to Unity Catalog. Which failure risk follows most closely from the unresolved behavior?

  1. Anyone allowed to download the model artifact can extract credentials beyond the model's intended data access.
  2. Recovery requires guessing traffic splits, permissions and served model versions during an outage.
  3. The client amplifies throttling and creates a self-sustaining inference outage.
  4. Manual and automated updates race, creating unexpected model routing during production traffic.

Explanation

Correct Answer

A:

This consequence follows from the specific unresolved condition. Anyone allowed to download the model artifact can extract credentials beyond the model's intended data access. The causal constraint is: Model artifacts should not serialize secrets; serving identities should resolve credentials securely at runtime.

Incorrect Answers

B:

That direct consequence is directed at a different custom model serving situation: A platform engineer creates a custom serving endpoint manually and assumes the exact settings can be recovered after an accidental deletion. The more immediate risk here is anyone allowed to download the model artifact can extract credentials beyond the model's intended data access.

C:

That direct consequence is directed at a different custom model serving situation: A real-time client retries every 429 rate-limit error immediately in an unbounded loop and multiplies load on the serving endpoint. The more immediate risk here is anyone allowed to download the model artifact can extract credentials beyond the model's intended data access.

D:

That direct consequence is directed at a different custom model serving situation: A team edits a model endpoint through the UI while its CI pipeline concurrently applies an older configuration and reverts the intended traffic split. The more immediate risk here is anyone allowed to download the model artifact can extract credentials beyond the model's intended data access.

Certified Machine Learning Professional Practice Tests