cert
cert-1
cert-2

Pass Google Professional Machine Learning Engineer 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
Professional Machine Learning Engineer Exam - Verified By Experts
Professional Machine Learning Engineer Premium Bundle
$29.98

Professional Machine Learning Engineer Premium Bundle

$79.99
$109.97
  • Premium File 402 Questions & Answers. Last update: Nov 13, 2026
  • Training Course 69 Video Lectures
  • Study Guide 376 Pages
 
$109.97
$79.99
accept 47 downloads in last 7 days
block-screenshots
Purchase Google Professional Machine Learning Engineer Exam Training Products Individually
Google Professional Machine Learning Engineer Premium File
Premium File 402 Q&A
$76.99$69.99
Google Professional Machine Learning Engineer Video Training Course
Training Course 69 Lectures
$21.99 $19.99
Google Professional Machine Learning Engineer PDF Study Guide
Study Guide 376 Pages
$21.99 $19.99
Google Professional Machine Learning Engineer Practice Test 61

Question 600

While reproducing a training orchestration incident in isolated staging, the following condition occurs: A scheduled training pipeline fails during feature validation but the team discovers the failure only when customers complain about stale predictions. The team requires an idempotent pipeline behavior and traceable evidence. Which configuration or procedure is the most appropriate correction?

  1. Retain the last healthy model and require canary validation before switching all prediction traffic.
  2. Record governed dataset snapshot and transformation versions as pipeline inputs linked to the resulting model artifact.
  3. Require inference contract and integration tests with representative requests before promoting each candidate artifact.
  4. Configure failure and stale-model alerts tied to actionable run-status and freshness service objectives.

Explanation

Correct Answer

D:

Configure failure and stale-model alerts tied to actionable run-status and freshness service objectives. This is the targeted corrective response for pipeline notification alert on silent failure. Orchestration without failure notification can leave models stale even when the last successful deployment was correct. Verify the diagnosis using: Inspect task execution states, failed-job logs, alert routing, pipeline-age metrics and owner escalation settings. Confirm success using: An injected validation failure alerts the responsible owner and the last healthy model continues serving.

Incorrect Answers

A:

Retain the last healthy model and require canary validation before switching all prediction traffic. This action addresses continuous training rollback protection, not the failure in the described pipeline notification alert on silent failure case. The targeted correction is: Configure failure and stale-model alerts tied to actionable run-status and freshness service objectives.

B:

Record governed dataset snapshot and transformation versions as pipeline inputs linked to the resulting model artifact. This action addresses model feature lineage for audit, not the failure in the described pipeline notification alert on silent failure case. The targeted correction is: Configure failure and stale-model alerts tied to actionable run-status and freshness service objectives.

C:

Require inference contract and integration tests with representative requests before promoting each candidate artifact. This action addresses continuous delivery integration contract tests, not the failure in the described pipeline notification alert on silent failure case. The targeted correction is: Configure failure and stale-model alerts tied to actionable run-status and freshness service objectives.

Question 601

During a postdeployment AI safety and reliability review, the following condition occurs: An assistant summarizes third-party documents and malicious attachments can contain hidden exfiltration instructions, with no content screening before model invocation. The model owner must provide repeatable evidence rather than a cosmetic dashboard change. Which technical explanation best accounts for the reported behavior?

  1. Prompt wording alone is not a reliable comprehensive safety boundary for public generative applications.
  2. External retrieval content can carry attacker instructions; data should not receive the authority of trusted application instructions.
  3. Excess prompt context can increase processing cost and latency without improving response accuracy.
  4. Screening helps detect malicious instructions or sensitive content crossing the model trust boundary.

Explanation

Correct Answer

D:

Screening helps detect malicious instructions or sensitive content crossing the model trust boundary. This explains the mechanism behind model armor untrusted content screening and why the described failure is possible. A discriminating investigation is: Inspect attachment ingestion, trust boundaries, malicious prompt examples and deployed Model Armor filter results. The corresponding repair is: Add appropriate Model Armor screening to untrusted inputs and outputs and reject or quarantine policy-violating content.

Incorrect Answers

A:

Prompt wording alone is not a reliable comprehensive safety boundary for public generative applications. This principle describes gen ai output safety policy enforcement, which is not the cause of the observed model armor untrusted content screening failure. The controlling explanation is: Screening helps detect malicious instructions or sensitive content crossing the model trust boundary.

B:

External retrieval content can carry attacker instructions; data should not receive the authority of trusted application instructions. This principle describes prompt injection through retrieved documents, which is not the cause of the observed model armor untrusted content screening failure. The controlling explanation is: Screening helps detect malicious instructions or sensitive content crossing the model trust boundary.

C:

Excess prompt context can increase processing cost and latency without improving response accuracy. This principle describes llm latency and cost token regression, which is not the cause of the observed model armor untrusted content screening failure. The controlling explanation is: Screening helps detect malicious instructions or sensitive content crossing the model trust boundary.

Question 602

During a staged restoration test at a secondary serving deployment, the following condition occurs: A model server scales down to zero expensive workers overnight but cannot meet the first morning burst because loading weights takes several minutes. The team must prove an actual user-visible improvement without weakening access controls. Which technical explanation best accounts for the reported behavior?

  1. Identity permission is not proof of network reachability; private serving also requires correct routing and name resolution.
  2. Reactive scaling cannot instantly serve requests when cold model initialization is long.
  3. CPU usage can be weakly related to accelerator or queue-bound inference workloads.
  4. Synchronous request limits cannot be solved merely by expanding the model context or retrying indefinitely.

Explanation

Correct Answer

B:

Reactive scaling cannot instantly serve requests when cold model initialization is long. This explains the mechanism behind autoscaling minimum capacity versus cold load and why the described failure is possible. A discriminating investigation is: Inspect idle cost, model initialization time, min replicas, burst arrival, queueing and request deadlines. The corresponding repair is: Set a justified warm minimum or scheduled capacity and balance initialization overhead against idle cost. This matters here because during a staged restoration test at a secondary serving deployment, the following condition occurs: A model server….

Incorrect Answers

A:

Identity permission is not proof of network reachability; private serving also requires correct routing and name resolution. This principle describes private vpc routing failure for serving, which is not the cause of the observed autoscaling minimum capacity versus cold load failure. The controlling explanation is: Reactive scaling cannot instantly serve requests when cold model initialization is long. This matters here because during a staged restoration test at a secondary serving deployment, the following condition occurs: A model server….

C:

CPU usage can be weakly related to accelerator or queue-bound inference workloads. This principle describes throughput-based autoscaling versus cpu metric, which is not the cause of the observed autoscaling minimum capacity versus cold load failure. The controlling explanation is: Reactive scaling cannot instantly serve requests when cold model initialization is long.

D:

Synchronous request limits cannot be solved merely by expanding the model context or retrying indefinitely. This principle describes online prediction timeout and batch fallback, which is not the cause of the observed autoscaling minimum capacity versus cold load failure. The controlling explanation is: Reactive scaling cannot instantly serve requests when cold model initialization is long.

Question 603

At a Google Cloud analytics team preparing a governed pilot, the following condition occurs: A financial regression model reports astonishing test accuracy because its validation query includes a post-settlement field derived from the target. The team must satisfy a reproducible low-code AI assessment. Which diagnostic check should be performed FIRST to isolate the described cause?

  1. Check whether real class labels exist and examine the standardized input distributions and cluster stability under different seeds.
  2. Inspect representative invoices, desired structured fields, supported processor output and field-level extraction errors.
  3. Inspect the timestamp ordering, seasonal patterns, horizon requirement, and the BigQuery ML model_type and time-series options.
  4. Inspect feature timestamps, label generation time, feature attributions, and whether the evaluation partition is independent.

Explanation

Correct Answer

D:

Inspect feature timestamps, label generation time, feature attributions, and whether the evaluation partition is independent. This inspects evidence relevant to bigquery ml ml.evaluate leakage detection. A label-derived future field leaks the outcome into input features and makes offline metrics deceptively strong. After identifying the cause, the matching correction is: Exclude post-outcome fields, create point-in-time valid training and evaluation partitions, and rerun ML.EVALUATE. Here, the relevant situation is: the following condition occurs: A financial regression model reports astonishing test accuracy because its….

Incorrect Answers

A:

Check whether real class labels exist and examine the standardized input distributions and cluster stability under different seeds. This examines bigquery ml kmeans customer segmentation rather than the specific mechanism reported here. It is not the decisive first check for bigquery ml ml.evaluate leakage detection. The relevant evidence is: Inspect feature timestamps, label generation time, feature attributions, and whether the evaluation partition is independent.

B:

Inspect representative invoices, desired structured fields, supported processor output and field-level extraction errors. This examines document ai structured invoice extraction rather than the specific mechanism reported here. It is not the decisive first check for bigquery ml ml.evaluate leakage detection. The relevant evidence is: Inspect feature timestamps, label generation time, feature attributions, and whether the evaluation partition is independent.

C:

Inspect the timestamp ordering, seasonal patterns, horizon requirement, and the BigQuery ML model_type and time-series options. This examines bigquery arima_plus forecast horizon rather than the specific mechanism reported here. It is not the decisive first check for bigquery ml ml.evaluate leakage detection. The relevant evidence is: Inspect feature timestamps, label generation time, feature attributions, and whether the evaluation partition is independent. Here, the relevant situation is: the following condition occurs: A financial regression model reports astonishing test accuracy because its….

Question 604

During a production ML inference release on Google Cloud, the following condition occurs: A model receives empty features for existing customers because online requests use string IDs with leading zeros while the source feature view cast them to integers. The service must meet its agreed quality and latency requirements. Which TWO complementary choices jointly establish the evidence and appropriate correction? Select TWO.

  1. Preserve stable canonical identifier types end-to-end and backfill only the affected feature records.
  2. Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures.
  3. Compare request rate, queue depth, GPU utilization, per-instance concurrency and p95 response latency.
  4. Benchmark a Cloud Run custom container against a managed Agent Platform endpoint and choose for workload fit.
  5. Set a justified warm minimum or scheduled capacity and balance initialization overhead against idle cost.

Explanation

Correct Answers

A:

Preserve stable canonical identifier types end-to-end and backfill only the affected feature records. This is the targeted corrective response for feature online entity key mismatch. Coercing identifier types can change keys, particularly when numeric-looking strings have meaningful leading zeros. Verify the diagnosis using: Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures. Confirm success using: Previously missed customer IDs retrieve the intended feature values without collapsing distinct leading-zero identifiers.

B:

Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures. This inspects evidence relevant to feature online entity key mismatch. Coercing identifier types can change keys, particularly when numeric-looking strings have meaningful leading zeros. After identifying the cause, the matching correction is: Preserve stable canonical identifier types end-to-end and backfill only the affected feature records.

Incorrect Answers

C:

Compare request rate, queue depth, GPU utilization, per-instance concurrency and p95 response latency. This is an action or diagnostic relevant to throughput-based autoscaling versus cpu metric, not one of the required two steps. In this scenario verify: Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures. Then correct: Preserve stable canonical identifier types end-to-end and backfill only the affected feature records.

D:

Benchmark a Cloud Run custom container against a managed Agent Platform endpoint and choose for workload fit. This is an action or diagnostic relevant to cloud run versus managed inference endpoint, not one of the required two steps. In this scenario verify: Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures. Then correct: Preserve stable canonical identifier types end-to-end and backfill only the affected feature records.

E:

Set a justified warm minimum or scheduled capacity and balance initialization overhead against idle cost. This is an action or diagnostic relevant to autoscaling minimum capacity versus cold load, not one of the required two steps. In this scenario verify: Compare requested entity key bytes, stored feature-group schema, casting rules and online lookup failures. Then correct: Preserve stable canonical identifier types end-to-end and backfill only the affected feature records.

Question 605

Within a jointly maintained Google Cloud data science workspace, the following condition occurs: A project declares model B superior even though A was evaluated on last quarter and B on a deliberately easier random sample. Collaborators must avoid expanding data access or breaking experiment reproducibility. Which technical explanation best accounts for the reported behavior?

  1. Skew concentrates otherwise distributed work on a single hot key, which extra workers alone may not resolve.
  2. Metrics from different data distributions are not directly comparable evidence of model improvement.
  3. MLOps provenance requires a recorded chain from code and data to model and deployment, not merely a friendly name.
  4. Trial metrics and artifact provenance must be linked to support valid experiment selection and release audits.

Explanation

Correct Answer

B:

Metrics from different data distributions are not directly comparable evidence of model improvement. This explains the mechanism behind experiment metric comparison with mismatched splits and why the described failure is possible. A discriminating investigation is: Inspect dataset and split fingerprints, label definitions, metric versions and evaluation timestamps for both experiment runs. The corresponding repair is: Register a common versioned holdout and comparable metrics in Agent Platform Experiments before ranking candidates.

Incorrect Answers

A:

Skew concentrates otherwise distributed work on a single hot key, which extra workers alone may not resolve. This principle describes managed spark join-key skew repair, which is not the cause of the observed experiment metric comparison with mismatched splits failure. The controlling explanation is: Metrics from different data distributions are not directly comparable evidence of model improvement.

C:

MLOps provenance requires a recorded chain from code and data to model and deployment, not merely a friendly name. This principle describes ml metadata lineage for production model, which is not the cause of the observed experiment metric comparison with mismatched splits failure. The controlling explanation is: Metrics from different data distributions are not directly comparable evidence of model improvement.

D:

Trial metrics and artifact provenance must be linked to support valid experiment selection and release audits. This principle describes pipeline experiment versus notebook-only tracking, which is not the cause of the observed experiment metric comparison with mismatched splits failure. The controlling explanation is: Metrics from different data distributions are not directly comparable evidence of model improvement.

Question 606

Within a jointly maintained Google Cloud data science workspace, the following condition occurs: A support assistant team reports a model improvement based solely on an unrestricted judge model's one-run preference, ignoring reference criteria and judge bias. Collaborators must avoid expanding data access or breaking experiment reproducibility. Which result is the strongest postchange evidence of success?

  1. Judge agreement against human standards improves and the decision is stable across repeated randomized evaluations.
  2. Each candidate's reported metrics resolve to its actual artifact and replayable configuration without manual lookups.
  3. A production model identifier resolves to its training execution, immutable artifacts, approvals and input dataset.
  4. Known records retrieve corresponding historical and current feature values for the intended entity without mismatched accounts.

Explanation

Correct Answer

A:

Judge agreement against human standards improves and the decision is stable across repeated randomized evaluations. This is specific acceptance evidence for llm-as-a-judge rubric reliability. LLM-based scoring can be sensitive to phrasing, order and model preferences; evaluation needs explicit calibration. It confirms the controlled correction: Build a constrained judge rubric with blind repeated comparisons and human-adjudicated calibration on representative examples. This matters here because within a jointly maintained Google Cloud data science workspace, the following condition occurs: A support assistant….

Incorrect Answers

B:

Each candidate's reported metrics resolve to its actual artifact and replayable configuration without manual lookups. This result could demonstrate success for pipeline experiment versus notebook-only tracking but not for the stated llm-as-a-judge rubric reliability issue. The direct test is: Judge agreement against human standards improves and the decision is stable across repeated randomized evaluations. This matters here because within a jointly maintained Google Cloud data science workspace, the following condition occurs: A support assistant….

C:

A production model identifier resolves to its training execution, immutable artifacts, approvals and input dataset. This result could demonstrate success for ml metadata lineage for production model but not for the stated llm-as-a-judge rubric reliability issue. The direct test is: Judge agreement against human standards improves and the decision is stable across repeated randomized evaluations. This matters here because within a jointly maintained Google Cloud data science workspace, the following condition occurs: A support assistant….

D:

Known records retrieve corresponding historical and current feature values for the intended entity without mismatched accounts. This result could demonstrate success for feature store online and offline entity alignment but not for the stated llm-as-a-judge rubric reliability issue. The direct test is: Judge agreement against human standards improves and the decision is stable across repeated randomized evaluations.

Question 607

During a staged restoration test at a secondary serving deployment, the following condition occurs: An online recommender test randomly selects a model for every click, exposing one person to both variants and confusing conversion attribution. The team must prove an actual user-visible improvement without weakening access controls. Which outcome most directly demonstrates a successful, measurable fix?

  1. Repeated requests from the same test user stay on one variant and conversion comparisons preserve randomized balance.
  2. The nightly job completes within the agreed SLA without idle real-time serving charges.
  3. Latency and memory decline on target hardware while validation degradation stays within the approved threshold.
  4. A controlled failed rollout restores the prior model and returns errors below the service objective.

Explanation

Correct Answer

A:

Repeated requests from the same test user stay on one variant and conversion comparisons preserve randomized balance. This is specific acceptance evidence for a/b assignment consistency for user journeys. Per-request routing can mix treatments within a user and contaminate a longitudinal A/B experiment. It confirms the controlled correction: Use stable cohort-level assignment and record model identity on requests and measured outcomes.

Incorrect Answers

B:

The nightly job completes within the agreed SLA without idle real-time serving charges. This result could demonstrate success for batch versus online inference schedule but not for the stated a/b assignment consistency for user journeys issue. The direct test is: Repeated requests from the same test user stay on one variant and conversion comparisons preserve randomized balance.

C:

Latency and memory decline on target hardware while validation degradation stays within the approved threshold. This result could demonstrate success for inference optimization using quantization but not for the stated a/b assignment consistency for user journeys issue. The direct test is: Repeated requests from the same test user stay on one variant and conversion comparisons preserve randomized balance.

D:

A controlled failed rollout restores the prior model and returns errors below the service objective. This result could demonstrate success for model traffic rollback on high error rate but not for the stated a/b assignment consistency for user journeys issue. The direct test is: Repeated requests from the same test user stay on one variant and conversion comparisons preserve randomized balance.

Question 608

At a Google Cloud analytics team preparing a governed pilot, the following condition occurs: An international retailer manually sends each product description to an English-only classifier although the business first needs translated content in several supported languages. The team must satisfy a reproducible low-code AI assessment. Which statement identifies the primary reason for this failure?

  1. Classification labels cannot directly represent unrestricted continuous outcomes; SQL regression models match numeric targets.
  2. Translation and classification are different tasks; an industry language API directly addresses supported cross-language conversion.
  3. Model size alone does not ensure suitable task support, usage rights or production economics.
  4. Object or image classification only identifies image categories; document understanding targets structured text fields.

Explanation

Correct Answer

B:

Translation and classification are different tasks; an industry language API directly addresses supported cross-language conversion. This explains the mechanism behind translate api for multilingual product descriptions and why the described failure is possible. A discriminating investigation is: Inspect source languages, target locale requirements, formatting preservation and translation quality on a multilingual sample. The corresponding repair is: Use Cloud Translation API for supported text translation, then separately validate downstream classification against localized content.

Incorrect Answers

A:

Classification labels cannot directly represent unrestricted continuous outcomes; SQL regression models match numeric targets. This principle describes bigquery ml linear regression for continuous value, which is not the cause of the observed translate api for multilingual product descriptions failure. The controlling explanation is: Translation and classification are different tasks; an industry language API directly addresses supported cross-language conversion.

C:

Model size alone does not ensure suitable task support, usage rights or production economics. This principle describes model garden task and license selection, which is not the cause of the observed translate api for multilingual product descriptions failure. The controlling explanation is: Translation and classification are different tasks; an industry language API directly addresses supported cross-language conversion.

D:

Object or image classification only identifies image categories; document understanding targets structured text fields. This principle describes document ai structured invoice extraction, which is not the cause of the observed translate api for multilingual product descriptions failure. The controlling explanation is: Translation and classification are different tasks; an industry language API directly addresses supported cross-language conversion.

Question 609

While reproducing a training orchestration incident in isolated staging, the following condition occurs: A Kubeflow preprocessing task is evicted repeatedly because it requests little memory despite materializing large embeddings inside the container. The team requires an idempotent pipeline behavior and traceable evidence. Which TWO selections represent the correct investigation and remediation together? Select TWO.

  1. Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once.
  2. Inspect task lineage, retries, durable checkpoints, object-store pressure and failed worker logs.
  3. Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior.
  4. Train only on adequately matured labeled cohorts and monitor recent feature drift separately until outcomes arrive.
  5. Publish one versioned pipeline package and promote it with reviewed environment-specific parameters.

Explanation

Correct Answers

A:

Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once. This is the targeted corrective response for custom kfp component resource limits. Kubernetes resource limits constrain component runtime even when the model's training job itself has spare capacity. Verify the diagnosis using: Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior. Confirm success using: The task completes within approved resources with predictable cost and produces the same number of embeddings.

C:

Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior. This inspects evidence relevant to custom kfp component resource limits. Kubernetes resource limits constrain component runtime even when the model's training job itself has spare capacity. After identifying the cause, the matching correction is: Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once.

Incorrect Answers

B:

Inspect task lineage, retries, durable checkpoints, object-store pressure and failed worker logs. This is an action or diagnostic relevant to ray distributed task failure isolation, not one of the required two steps. In this scenario verify: Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior. Then correct: Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once.

D:

Train only on adequately matured labeled cohorts and monitor recent feature drift separately until outcomes arrive. This is an action or diagnostic relevant to scheduled retraining on delayed ground truth, not one of the required two steps. In this scenario verify: Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior. Then correct: Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once.

E:

Publish one versioned pipeline package and promote it with reviewed environment-specific parameters. This is an action or diagnostic relevant to pipeline environment parameter promotion, not one of the required two steps. In this scenario verify: Inspect Kubernetes task events, memory usage, component resource requests and container data-loading behavior. Then correct: Tune component resource requests/limits and stream or partition embeddings rather than materializing every vector at once.

Question 610

At a Google Cloud analytics team preparing a governed pilot, the following condition occurs: A retailer has no trustworthy segment labels but attempts a supervised classifier with synthetic classes supplied by the sales team. The team must satisfy a reproducible low-code AI assessment. What acceptance result verifies the intended behavior after remediation?

  1. An unseen labeled cohort receives probabilities for the intended positive class with a calibrated operating threshold.
  2. On held-out questions, answers remain grounded while input tokens and p95 response latency decline.
  3. A trained candidate reaches the agreed quality threshold without maintaining unsupported bespoke training infrastructure.
  4. Stable clusters reveal coherent customer behavior without pretending an unsupervised assignment is known supervised ground truth.

Explanation

Correct Answer

D:

Stable clusters reveal coherent customer behavior without pretending an unsupervised assignment is known supervised ground truth. This is specific acceptance evidence for bigquery ml kmeans customer segmentation. K-means discovers unlabeled similarity groups; fabricating labels would make supervised accuracy meaningless. It confirms the controlled correction: Train an appropriately scaled BigQuery ML KMEANS model and assess cluster cohesion, size and business interpretability. Here, the relevant situation is: the following condition occurs: A retailer has no trustworthy segment labels but attempts a supervised classifier….

Incorrect Answers

A:

An unseen labeled cohort receives probabilities for the intended positive class with a calibrated operating threshold. This result could demonstrate success for bigquery ml logistic model for conversion probability but not for the stated bigquery ml kmeans customer segmentation issue. The direct test is: Stable clusters reveal coherent customer behavior without pretending an unsupervised assignment is known supervised ground truth.

B:

On held-out questions, answers remain grounded while input tokens and p95 response latency decline. This result could demonstrate success for gemini prompt context token budget but not for the stated bigquery ml kmeans customer segmentation issue. The direct test is: Stable clusters reveal coherent customer behavior without pretending an unsupervised assignment is known supervised ground truth.

C:

A trained candidate reaches the agreed quality threshold without maintaining unsupported bespoke training infrastructure. This result could demonstrate success for automl tabular supervised model selection but not for the stated bigquery ml kmeans customer segmentation issue. The direct test is: Stable clusters reveal coherent customer behavior without pretending an unsupervised assignment is known supervised ground truth.

Professional Machine Learning Engineer Practice Tests