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 89

Question 880

A production ML review contains this situation: A fairness reviewer needs the difference in false-negative rates between two approved cohorts, but the monitor computes an aggregate without cohort labels. What production-safe change best matches the evidence?

  1. Evaluate performance only on sufficiently matured matched predictions and report pending labels separately.
  2. Configure a documented threshold with the responsible on-call team and a tested delivery route.
  3. Calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards.
  4. Retain a stable reference comparison in addition to short-term change detection.

Explanation

Correct Answer

C:

This corrects the relevant failure boundary instead of merely hiding the symptom. Calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards. The issue matters because a material disparity is hidden inside the overall average model performance.

Incorrect Answers

A:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A fraud model predicts instantly but labels arrive 21 days later; an inference dashboard treats unlabelled transactions as negative examples. The relevant corrective action here is calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards.

B:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A fraud-feature drift monitor crosses its threshold but the alert has no assigned recipient and no incident ownership. The relevant corrective action here is calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards.

D:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A streaming payments monitor always compares today with the previous hour, and a slow week-long distribution drift escapes because adjacent hours differ only slightly. The relevant corrective action here is calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards.

Question 881

Review this production model incident: A recommendation team wraps a large pandas UDF around entire customer histories, then discovers some partitions exceed worker memory while others finish quickly. Which failure risk follows most closely from the unresolved behavior?

  1. One hot customer group repeatedly crashes tasks and stalls distributed tuning.
  2. The rewritten job runs only on one worker or fails during model serialization.
  3. Trials are lost or repeated even when compute nodes appear healthy.
  4. Training stalls on memory pressure even while unrelated cluster nodes are underutilized.

Explanation

Correct Answer

A:

This consequence follows from the specific unresolved condition. One hot customer group repeatedly crashes tasks and stalls distributed tuning. The causal constraint is: Pandas-function distribution requires bounded partition or group size, not just parallel execution of arbitrary large pandas objects.

Incorrect Answers

B:

That direct consequence is directed at a different scaling and tuning situation: A team switches a SparkML training stage to Ray without verifying that its chosen estimator supports Ray's distributed fit contracts. The more immediate risk here is one hot customer group repeatedly crashes tasks and stalls distributed tuning.

C:

That direct consequence is directed at a different scaling and tuning situation: A researcher parallelizes Optuna trials while sharing one writable SQLite file on a fragile network mount and observes duplicate reservations and storage locks. The more immediate risk here is one hot customer group repeatedly crashes tasks and stalls distributed tuning.

D:

That direct consequence is directed at a different scaling and tuning situation: A single-node model training run spends almost all time swapping a 40 GB feature matrix on a 16 GB VM; no distributed version exists. The more immediate risk here is one hot customer group repeatedly crashes tasks and stalls distributed tuning.

Question 882

A production ML review contains this situation: An automated retraining job triggers whenever a numerical feature mean shifts by 0.1, regardless of normal seasonal changes or sample size. Which statement best explains the failure mode?

  1. Champion selection must enforce critical segment-level guardrails in addition to aggregate ranking metrics.
  2. Model candidates need evaluation on the same versioned holdout and metric definition for fair comparison.
  3. Drift-triggered retraining needs statistically and operationally justified thresholds, not arbitrary raw metric movement.
  4. Small measured differences need uncertainty or minimum-evidence gates to justify risky promotion.

Explanation

Correct Answer

C:

The technical constraint is specific to the reported failure. Drift-triggered retraining needs statistically and operationally justified thresholds, not arbitrary raw metric movement. To test it, compare baseline seasonality, sample sizes and repeated drift statistics before each retrain event.

Incorrect Answers

A:

That underlying principle is directed at a different automated retraining situation: A new fraud classifier improves overall F1 but doubles false negatives for high-value payment accounts, and an automated policy chooses it on F1 alone. The current incident instead turns on drift-triggered retraining needs statistically and operationally justified thresholds, not arbitrary raw metric movement.

B:

That underlying principle is directed at a different automated retraining situation: A retraining pipeline ranks candidate models using metrics calculated on different dataset versions, then selects the numerically highest result. The current incident instead turns on drift-triggered retraining needs statistically and operationally justified thresholds, not arbitrary raw metric movement.

D:

That underlying principle is directed at a different automated retraining situation: A new model beats the champion by 0.1 percentage points on a tiny evaluation set, and the team automatically promotes it despite large uncertainty. The current incident instead turns on drift-triggered retraining needs statistically and operationally justified thresholds, not arbitrary raw metric movement.

Question 883

Review this production model incident: A churn experiment separately scripts feature scaling in training but omits that scaling when the deployed prediction job loads the classifier. Which mitigation resolves the defect rather than concealing it?

  1. Evaluate the model with class-sensitive metrics and choose thresholds aligned with false-positive and missed-fraud tradeoffs.
  2. Fit and persist a unified PipelineModel containing scaling and model stages, then use it for inference.
  3. Apply VectorAssembler to produce the features vector before fitting the chosen learning algorithm.
  4. Load the fitted PipelineModel and transform the full batch DataFrame through supported Spark execution.

Explanation

Correct Answer

B:

This corrects the relevant failure boundary instead of merely hiding the symptom. Fit and persist a unified PipelineModel containing scaling and model stages, then use it for inference. The issue matters because predictions change because the deployed estimator receives unscaled columns it was never trained on.

Incorrect Answers

A:

That corrective action 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. The relevant corrective action here is fit and persist a unified PipelineModel containing scaling and model stages, then use it for inference.

C:

That corrective action is directed at a different using spark ml situation: A team wants to convert several numeric inputs into one features vector but treats VectorAssembler as a clustering Estimator that should output predictions. The relevant corrective action here is fit and persist a unified PipelineModel containing scaling and model stages, then use it for inference.

D:

That corrective action is directed at a different using spark ml situation: A logistics model must score 60 million daily routes already in Delta but the scoring script collects each route into Python before calling predict. The relevant corrective action here is fit and persist a unified PipelineModel containing scaling and model stages, then use it for inference.

Question 884

Consider the following fictional Databricks production case: A scoring endpoint quietly moves from model v7 to v8 during a rollout but an inference trend aggregates both versions in one error curve. Which implementation is most appropriate for the stated incident?

  1. Configure a documented threshold with the responsible on-call team and a tested delivery route.
  2. Align baseline and current cohort definitions before computing temporal drift.
  3. Compute comparable version-specific performance trends and retain traffic-share context.
  4. Calculate slice-specific error rates and a documented derived disparity metric with privacy safeguards.

Explanation

Correct Answer

C:

This corrects the relevant failure boundary instead of merely hiding the symptom. Compute comparable version-specific performance trends and retain traffic-share context. The issue matters because a regression in v8 is masked by higher-volume predictions from v7.

Incorrect Answers

A:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A fraud-feature drift monitor crosses its threshold but the alert has no assigned recipient and no incident ownership. The relevant corrective action here is compute comparable version-specific performance trends and retain traffic-share context.

B:

That corrective action 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. The relevant corrective action here is compute comparable version-specific performance trends and retain traffic-share context.

D:

That corrective action is directed at a different drift detection and lakehouse monitoring situation: A fairness reviewer needs the difference in false-negative rates between two approved cohorts, but the monitor computes an aggregate without cohort labels. The relevant corrective action here is compute comparable version-specific performance trends and retain traffic-share context.

Question 885

A production ML review contains this 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. What is the most material immediate risk in this situation?

  1. Traffic growth is mistaken for increasing risk because the raw count rises mechanically.
  2. An apparent overnight model failure is only a grouping artifact and triggers costly false alerts.
  3. A regression in v8 is masked by higher-volume predictions from v7.
  4. The live population drifts far from model training even though daily changes remain modest.

Explanation

Correct Answer

C:

This consequence follows from the specific unresolved condition. A regression in v8 is masked by higher-volume predictions from v7. The causal constraint is: Performance trends require model-version provenance to attribute changes to the correct release.

Incorrect Answers

A:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: A monitoring team wants a business metric for the share of transactions exceeding a risk threshold but records only the raw count of high-risk transactions. The more immediate risk here is a regression in v8 is masked by higher-volume predictions from v7.

B:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: A model's prediction error appears to spike at 2 a.m. local time but the monitoring table groups timestamps in UTC for a globally distributed region. The more immediate risk here is a regression in v8 is masked by higher-volume predictions from v7.

D:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: A model trained on last year's customer mix is monitored only against yesterday's already shifted cohort, so its original training-population mismatch is hidden. The more immediate risk here is a regression in v8 is masked by higher-volume predictions from v7.

Question 886

The engineering team encounters the following issue: A model performance dashboard compares this week's labels to last week's predictions without joining by stable request ID or consistent outcome horizon. What investigation would most effectively isolate this behavior?

  1. Audit request identifiers, event timestamps and join cardinality in the performance computation.
  2. Review the metric query's output grain, fields and result-table access against data classification.
  3. Inspect received alert fields and the corresponding monitor query, model tag and comparison window.
  4. Inspect cohort sizes, allowed sensitive fields and uncertainty around the reported subgroup error rate.

Explanation

Correct Answer

A:

This is the most discriminating check for the observed symptoms. Audit request identifiers, event timestamps and join cardinality in the performance computation. The underlying technical issue is that an inference table needs correct prediction-to-label linkage for trustworthy observed performance metrics.

Incorrect Answers

B:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A monitor owner writes a custom metric that logs unaggregated account-level health data in a broadly shared results table. For the stated incident, the decisive observation is audit request identifiers, event timestamps and join cardinality in the performance computation.

C:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A drift alert fires but its message contains only the word anomaly without dataset, model version or baseline window. For the stated incident, the decisive observation is audit request identifiers, event timestamps and join cardinality in the performance computation.

D:

That diagnostic evidence is directed at a different drift detection and lakehouse monitoring situation: A demographic fairness review uses a tiny sensitive subgroup with three labeled examples and reports its observed error as definitive. For the stated incident, the decisive observation is audit request identifiers, event timestamps and join cardinality in the performance computation.

Question 887

A production ML review contains this situation: An integration caches predictions without recording the model version and returns yesterday's values after a controlled rollback. Which diagnostic check provides the strongest direct evidence?

  1. Compare sandbox/prod identities, model grants and sanitized deployment authorization errors.
  2. Compare response creation time, endpoint model version and cache keys before and after rollback.
  3. Scan the serialized custom model artifact and logs for token material and audit its access history.
  4. Compare training import versions and logged model environment metadata with serving import failures.

Explanation

Correct Answer

B:

This is the most discriminating check for the observed symptoms. Compare response creation time, endpoint model version and cache keys before and after rollback. The underlying technical issue is that serving responses that are cached or audited need model-version provenance and appropriate expiration rules.

Incorrect Answers

A:

That diagnostic evidence is directed at a different custom model serving situation: A test engineer can create a model-serving endpoint in a sandbox but the production deployment fails because the automation identity lacks registered-model access. For the stated incident, the decisive observation is compare response creation time, endpoint model version and cache keys before and after rollback.

C:

That diagnostic evidence is directed at a different custom model serving situation: An engineer logs a customer-specific API token inside the pickled PythonModel object before registering it to Unity Catalog. For the stated incident, the decisive observation is compare response creation time, endpoint model version and cache keys before and after rollback.

D:

That diagnostic evidence is directed at a different custom model serving situation: A team logs custom MLflow model weights but forgets to include required Python package versions in the model environment. For the stated incident, the decisive observation is compare response creation time, endpoint model version and cache keys before and after rollback.

Question 888

Review this production model incident: A fairness reviewer needs the difference in false-negative rates between two approved cohorts, but the monitor computes an aggregate without cohort labels. What is the central engineering constraint behind this behavior?

  1. Alert payloads should carry sufficient metric and lineage context for safe triage.
  2. A custom fairness comparison needs matched labels, model predictions and governed subgroup definitions.
  3. Performance trends require model-version provenance to attribute changes to the correct release.
  4. Reference populations should match relevant seasonality and business context when interpreting drift.

Explanation

Correct Answer

B:

The technical constraint is specific to the reported failure. A custom fairness comparison needs matched labels, model predictions and governed subgroup definitions. To test it, inspect subgroup membership, prediction/label joins and false-negative denominator in the source table.

Incorrect Answers

A:

That underlying principle is directed at a different drift detection and lakehouse monitoring situation: A drift alert fires but its message contains only the word anomaly without dataset, model version or baseline window. The current incident instead turns on a custom fairness comparison needs matched labels, model predictions and governed subgroup definitions.

C:

That underlying principle 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 current incident instead turns on a custom fairness comparison needs matched labels, model predictions and governed subgroup definitions.

D:

That underlying principle is directed at a different drift detection and lakehouse monitoring situation: An online feature monitor compares weekend shopping to weekday reference data and treats expected weekend behavior as a model failure. The current incident instead turns on a custom fairness comparison needs matched labels, model predictions and governed subgroup definitions.

Question 889

Consider the following fictional Databricks production case: A test engineer can create a model-serving endpoint in a sandbox but the production deployment fails because the automation identity lacks registered-model access. Which observation most directly tests the suspected failure boundary?

  1. Replay valid, missing and nonnumeric fixture fields against the PyFunc predict interface.
  2. Compare sandbox/prod identities, model grants and sanitized deployment authorization errors.
  3. Inspect rate-limit response headers, client retry timeline and duplicate request identifiers.
  4. Inspect model artifact source, planned three-level Unity Catalog name and effective registration permissions.

Explanation

Correct Answer

B:

This is the most discriminating check for the observed symptoms. Compare sandbox/prod identities, model grants and sanitized deployment authorization errors. The underlying technical issue is that serving deployment permissions must include authorization to use the intended governed model and endpoint resources.

Incorrect Answers

A:

That diagnostic evidence is directed at a different custom model serving situation: A custom PyFunc's predict method assumes every request contains a numeric feature that is optional under the documented inference schema. For the stated incident, the decisive observation is compare sandbox/prod identities, model grants and sanitized deployment authorization errors.

C:

That diagnostic evidence 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. For the stated incident, the decisive observation is compare sandbox/prod identities, model grants and sanitized deployment authorization errors.

D:

That diagnostic evidence is directed at a different custom model serving situation: A research group wants to register a custom classification model in Unity Catalog but uses a local path as its complete model identity and has no governed model name. For the stated incident, the decisive observation is compare sandbox/prod identities, model grants and sanitized deployment authorization errors.

Question 890

In an enterprise ML workflow, the reported issue is: A binary model's average predicted probability remains 0.4, but outcomes show that 0.8 predictions are now correct only half the time. What likely operational or model-quality harm does this issue create?

  1. The metric fails or silently excludes malformed observations, distorting the reported trend.
  2. Downstream risk thresholds overtrust predicted probabilities and misprice decisions.
  3. Gradual cumulative drift becomes invisible despite material divergence from the trained population.
  4. Small-cell disclosure and unstable rates cause privacy risk and misleading fairness decisions.

Explanation

Correct Answer

B:

This consequence follows from the specific unresolved condition. Downstream risk thresholds overtrust predicted probabilities and misprice decisions. The causal constraint is: Calibration drift requires comparing predicted probabilities with observed outcome frequencies, not just prediction means.

Incorrect Answers

A:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: An ML owner adds a custom metric computed from the average of a string-typed currency column without validating conversion. The more immediate risk here is downstream risk thresholds overtrust predicted probabilities and misprice decisions.

C:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: A streaming payments monitor always compares today with the previous hour, and a slow week-long distribution drift escapes because adjacent hours differ only slightly. The more immediate risk here is downstream risk thresholds overtrust predicted probabilities and misprice decisions.

D:

That direct consequence is directed at a different drift detection and lakehouse monitoring situation: A demographic fairness review uses a tiny sensitive subgroup with three labeled examples and reports its observed error as definitive. The more immediate risk here is downstream risk thresholds overtrust predicted probabilities and misprice decisions.

Certified Machine Learning Professional Practice Tests