Exam Bundle

Build a BigQuery ML time-series forecasting model with the timestamp and product series configured for seasonal forecasting. This action could be suitable for a different engineering incident: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. It does not directly correct the reported Westhaven Marketplace failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Create a multi-series BigQuery ML forecast keyed by store identity and the event date rather than pooling locations into one series. This action could be suitable for a different engineering incident: A retailer wants separate forecasts for hundreds of stores but inadvertently aggregates all locations into one time series. It does not directly correct the reported Westhaven Marketplace failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. This action could be suitable for a different engineering incident: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not directly correct the reported Westhaven Marketplace failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines. This is evidence for a different corrective change: Build a BigQuery ML time-series forecasting model with the timestamp and product series configured for seasonal forecasting. That other change addresses: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. It does not validate the specific Westhaven Marketplace remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

A controlled dataset with nulls produces complete training rows and a per-column missingness audit without label leakage. This is evidence for a different corrective change: Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. That other change addresses: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not validate the specific Westhaven Marketplace remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Forecasts retain store IDs and independent store-level holdout errors are available for inspection. This is evidence for a different corrective change: Create a multi-series BigQuery ML forecast keyed by store identity and the event date rather than pooling locations into one series. That other change addresses: A retailer wants separate forecasts for hundreds of stores but inadvertently aggregates all locations into one time series. It does not validate the specific Westhaven Marketplace remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Use a BigQuery ML recommendation approach such as matrix factorization with appropriate user, item, and interaction data. This action could be suitable for a different engineering incident: A media platform seeks implicit user-item recommendations but trains an ordinary numeric sales regression with user IDs as magnitudes. It does not directly correct the reported Sunset Commerce failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Execute governed BigQuery ML scoring in the approved data location without unnecessary cross-region data export. This action could be suitable for a different engineering incident: A regulated team moves data extracts to a different region for periodic ML scoring despite a residency requirement for the source dataset. It does not directly correct the reported Sunset Commerce failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. This action could be suitable for a different engineering incident: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not directly correct the reported Sunset Commerce failure: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The discriminating acceptance check here is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

A controlled dataset with nulls produces complete training rows and a per-column missingness audit without label leakage. This is evidence for a different corrective change: Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. That other change addresses: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not validate the specific Sunset Commerce remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Held-out user-item recommendations rank relevant items more effectively than a non-personalized popularity baseline. This is evidence for a different corrective change: Use a BigQuery ML recommendation approach such as matrix factorization with appropriate user, item, and interaction data. That other change addresses: A media platform seeks implicit user-item recommendations but trains an ordinary numeric sales regression with user IDs as magnitudes. It does not validate the specific Sunset Commerce remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

The job location and audit logs show local scoring, and no unauthorized cross-region export occurs. This is evidence for a different corrective change: Execute governed BigQuery ML scoring in the approved data location without unnecessary cross-region data export. That other change addresses: A regulated team moves data extracts to a different region for periodic ML scoring despite a residency requirement for the source dataset. It does not validate the specific Sunset Commerce remediation for: A retailer's churn table has a binary cancellation label, but its analyst configures a continuous-outcome regression model and cannot interpret the scores as cancellation probabilities. The necessary check instead is: The holdout scoring job returns calibrated class probabilities and the recorded classification metrics replace regression error measures.

Create a multi-series BigQuery ML forecast keyed by store identity and the event date rather than pooling locations into one series. This action could be suitable for a different engineering incident: A retailer wants separate forecasts for hundreds of stores but inadvertently aggregates all locations into one time series. It does not directly correct the reported Evergreen Energy failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. This action could be suitable for a different engineering incident: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not directly correct the reported Evergreen Energy failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. This action could be suitable for a different engineering incident: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not directly correct the reported Evergreen Energy failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Forecasts retain store IDs and independent store-level holdout errors are available for inspection. This is evidence for a different corrective change: Create a multi-series BigQuery ML forecast keyed by store identity and the event date rather than pooling locations into one series. That other change addresses: A retailer wants separate forecasts for hundreds of stores but inadvertently aggregates all locations into one time series. It does not validate the specific Evergreen Energy remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

The held-out task rubric shows a measurable gain for the tuned candidate without contaminating validation examples. This is evidence for a different corrective change: Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. That other change addresses: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not validate the specific Evergreen Energy remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

A controlled dataset with nulls produces complete training rows and a per-column missingness audit without label leakage. This is evidence for a different corrective change: Define and fit an explicit BigQuery ML missing-value imputation strategy and track the percentage of imputed records. That other change addresses: A product-cost prediction query silently drops rows with missing numeric features, biasing the downstream training sample. It does not validate the specific Evergreen Energy remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. This action could be suitable for a different engineering incident: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not directly correct the reported Crescent Utilities failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Validate prediction input column names and types against the registered BigQuery ML model signature before scoring. This action could be suitable for a different engineering incident: A fraud team passes a renamed transaction field to ML.PREDICT and silently accepts null predictions from an incompatible scoring schema. It does not directly correct the reported Crescent Utilities failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Execute governed BigQuery ML scoring in the approved data location without unnecessary cross-region data export. This action could be suitable for a different engineering incident: A regulated team moves data extracts to a different region for periodic ML scoring despite a residency requirement for the source dataset. It does not directly correct the reported Crescent Utilities failure: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The discriminating acceptance check here is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

The job location and audit logs show local scoring, and no unauthorized cross-region export occurs. This is evidence for a different corrective change: Execute governed BigQuery ML scoring in the approved data location without unnecessary cross-region data export. That other change addresses: A regulated team moves data extracts to a different region for periodic ML scoring despite a residency requirement for the source dataset. It does not validate the specific Crescent Utilities remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

A deliberately renamed required feature fails the preflight while a matching schema yields non-null results. This is evidence for a different corrective change: Validate prediction input column names and types against the registered BigQuery ML model signature before scoring. That other change addresses: A fraud team passes a renamed transaction field to ML.PREDICT and silently accepts null predictions from an incompatible scoring schema. It does not validate the specific Crescent Utilities remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

The held-out task rubric shows a measurable gain for the tuned candidate without contaminating validation examples. This is evidence for a different corrective change: Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. That other change addresses: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not validate the specific Crescent Utilities remediation for: A utility forecasts numeric daily electricity consumption, but the SQL modeling job uses a binary classifier and emits only discrete classes. The necessary check instead is: A fresh holdout returns consumption quantities and reports MAE or RMSE against measured numeric outcomes.

Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. This action could be suitable for a different engineering incident: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not directly correct the reported Vertex Retail Cooperative failure: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The discriminating acceptance check here is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.

Apply BigQuery ML K-means clustering to meaningful standardized unlabeled behavior features and inspect resulting segments. This action could be suitable for a different engineering incident: An operations team wants to segment unlabeled customer behavior yet supplies made-up class labels to a supervised classifier. It does not directly correct the reported Vertex Retail Cooperative failure: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The discriminating acceptance check here is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.

Run BigQuery ML prediction against the governed input table with ML.PREDICT and the recorded feature mapping. This action could be suitable for a different engineering incident: A finance analyst has a trained BigQuery ML model but exports raw coefficients to a spreadsheet and manually reimplements inference with a mismatched schema. It does not directly correct the reported Vertex Retail Cooperative failure: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The discriminating acceptance check here is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.

Cluster assignments and separation diagnostics reveal coherent groups without requiring fabricated customer labels. This is evidence for a different corrective change: Apply BigQuery ML K-means clustering to meaningful standardized unlabeled behavior features and inspect resulting segments. That other change addresses: An operations team wants to segment unlabeled customer behavior yet supplies made-up class labels to a supervised classifier. It does not validate the specific Vertex Retail Cooperative remediation for: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The necessary check instead is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.

The held-out task rubric shows a measurable gain for the tuned candidate without contaminating validation examples. This is evidence for a different corrective change: Prepare governed, task-labeled examples in BigQuery and use the documented Gemini tuning workflow where the model and region support it. That other change addresses: A team requests domain-specific Gemini fine-tuning from curated BigQuery examples but repeatedly rewrites prompts instead of evaluating the supported tuning path. It does not validate the specific Vertex Retail Cooperative remediation for: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The necessary check instead is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.

Prediction output rows and model metadata match the SQL inference schema on a controlled sample without spreadsheet recoding. This is evidence for a different corrective change: Run BigQuery ML prediction against the governed input table with ML.PREDICT and the recorded feature mapping. That other change addresses: A finance analyst has a trained BigQuery ML model but exports raw coefficients to a spreadsheet and manually reimplements inference with a mismatched schema. It does not validate the specific Vertex Retail Cooperative remediation for: A marketplace predicts daily demand for each product but fits a static linear model without seasonal timestamps and misses weekly demand cycles. The necessary check instead is: Out-of-time product forecasts capture repeating weekly patterns and are compared against naive seasonal baselines.