An e-commerce organization wants to build a machine learning solution to categorize customer support tickets. The tickets contain unstructured data, including free-form text descriptions and uploaded product images showing damaged items. The development team has minimal machine learning expertise and wants a solution that automatically handles feature engineering, architecture selection, and model training without requiring custom deep learning code. Which Google Cloud approach should the organization use?

Train custom models using Vertex AI AutoML for image and text data.: ### **What Vertex AI AutoML is** **Vertex AI AutoML** is a suite of automated machine learning capabilities within Google Cloud designed to enable developers and data practitioners to train high-quality, custom machine learning models with minimal coding and without requiring deep machine learning expertise. It automates complex ML processes such as **feature engineering**, **neural architecture search**, hyperparameter tuning, and model evaluation. ### **How it meets the requirements** - **Unstructured data support (✓):** AutoML provides specialized workflows designed for unstructured data types, including **text classification**, sentiment analysis, entity extraction, **image classification**, and **object detection**. - **Automated feature engineering and model selection (✓):** AutoML automatically explores multiple model architectures and feature extraction methods to discover the optimal model for the provided training data. - **Minimal ML expertise required (✓):** The team does not need to write complex deep learning code in frameworks like TensorFlow or PyTorch; datasets can be uploaded, labeled, trained, and deployed directly through guided interfaces or high-level APIs. ### **Key advantages:** - **State-of-the-art architectures:** Utilizes Google's transfer learning and neural architecture search to produce accurate models from smaller labeled datasets. - **Managed infrastructure:** Model training and hyperparameter optimization run on Google-managed compute infrastructure with automatic scaling. - **Integrated workflow:** Centralizes dataset management, annotation, model training, evaluation metrics, and deployment within the Vertex AI ecosystem. - **Exportable artifacts:** Supports deploying models to managed endpoints for real-time inference or batch prediction pipelines. ### **Why this is optimal:** For unstructured data such as raw images and unstructured natural language text, traditional SQL-based or tabular tools are insufficient. **Vertex AI AutoML** bridges the gap between pre-trained off-the-shelf APIs and custom coding, delivering custom models tailored to specific business categories without the operational overhead of manual model development.

Automl Unstructured Text Image Classification | Unlock the power of your data in the cloud! Get hands-on with Google Cloud's core data services like BigQuery and Looker to validate your practical skills in data ingestion, analysis, and management, and earn your Associate Data Practitioner certification!

FundamentalAssociate Data Practitioner

A retail company stores several terabytes of structured transaction data in BigQuery tables. The data analytics team needs to train and evaluate a binary classification model to predict customer churn. The team wants to implement this solution using their existing standard SQL skills, without exporting or moving the data outside the data warehouse. Which solution should the team use?

Identify ML use cases for developing models by using BigQuery ML and AutoML

FundamentalAssociate Data Practitioner

A retail organization stores several terabytes of customer transaction and interaction data directly in BigQuery. The data analytics team needs to build predictive models for customer churn and group customers into distinct segments for targeted marketing campaigns. The team has strong SQL skills but lacks software engineering experience in Python or R, and they want to avoid exporting data to external systems or managing training infrastructure. Which Google Cloud capability should the team use?

FundamentalAssociate Data Practitioner

A data analytics team has loaded raw event tables into BigQuery. The team needs to develop a data transformation pipeline directly inside the data warehouse using standard SQL, establish table dependencies, implement automated data quality assertions, and track changes using Git-based version control without managing compute clusters or writing code in Java or Python. Which Google Cloud service should the team choose for this data transformation workload?

FundamentalAssociate Data Practitioner

Your team is deploying an event-driven data pipeline in Google Cloud. An Eventarc trigger is configured to listen for state changes in Dataflow jobs and route those events to an internal, authenticated Cloud Run service for automated post-processing. After creating the trigger, you notice that the Cloud Run service is never triggered, and the trigger logs display the following error message: The request was not authenticated. Either allow unauthenticated invocations or set the proper Authorization header. Which Identity and Access Management (IAM) configuration should you implement to resolve this issue securely?

FundamentalAssociate Data Practitioner

A data engineer is writing an automated bash script to ingest on-premises data into Google Cloud. The script needs to upload a local directory named /data/sales_records, which contains multiple nested subdirectories and CSV files, into a Cloud Storage bucket named gs://retail-analytics-lake. Which gcloud command should the engineer use to perform this upload?

Load data into Google Cloud storage systems using the appropriate tool (e.g., gcloud and BQ CLI, Storage Transfer Service, BigQuery Data Transfer Service, client libraries)

AdvancedProfessional Cloud Security Engineer

A security engineer is designing an automated DevSecOps workflow to manage vulnerability triage, gating, and remediation for container workloads across CI/CD pipelines and registry environments. The organization has established the following operational requirements: Automatically trigger Common Vulnerabilities and Exposures (CVE) security scans immediately when newly built container images are pushed to the registry. Enforce automated deployment guardrails by preventing any container images with vulnerability severities meeting or exceeding the High threshold from being pulled by runtime environments. Implement automated workflows to triage findings, trigger ticketing playbooks for base image patching, and establish cleanup lifecycle policies for vulnerable or stale artifacts. Which configuration strategy should the security engineer implement?

Associate Data Practitioner

Automl Unstructured Text Image Classification

Related questions