nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #262

You are developing a training pipeline for a new XGBoost classification model based on tabular data. The data is stored in a BigQuery table. You need to complete the following steps: 1. Randomly…

The correct answer is A. 1. Using Vertex AI Pipelines, add a component to divide the data into training and evaluation sets. To build an XGBoost classification model from BigQuery data, including data splitting, feature engineering, metric collection, and model comparison across runs, Vertex AI Pipelines should be used.

Submitted by helene.fr· Apr 18, 2026ML pipeline operationalization

Question

You are developing a training pipeline for a new XGBoost classification model based on tabular data. The data is stored in a BigQuery table. You need to complete the following steps: 1. Randomly split the data into training and evaluation datasets in a 65/35 ratio 2. Conduct feature engineering 3. Obtain metrics for the evaluation dataset 4. Compare models trained in different pipeline executions How should you execute these steps?

Options

  • A
    1. Using Vertex AI Pipelines, add a component to divide the data into training and evaluation sets,
  • B
    1. Using Vertex AI Pipelines, add a component to divide the data into training and evaluation sets,
  • C
    1. In BigQuery ML, use the CREATE MODEL statement with BOOSTED_TREE_CLASSIFIER as
  • D
    1. In BigQuery ML, use the CREATE MODEL statement with BOOSTED_TREE_CLASSIFIER as

How the community answered

(22 responses)
  • A
    86% (19)
  • C
    5% (1)
  • D
    9% (2)

Why each option

To build an XGBoost classification model from BigQuery data, including data splitting, feature engineering, metric collection, and model comparison across runs, Vertex AI Pipelines should be used.

A1. Using Vertex AI Pipelines, add a component to divide the data into training and evaluation sets,Correct

Vertex AI Pipelines are ideal for orchestrating complex machine learning workflows, enabling custom components for specific tasks like data splitting and feature engineering, and providing a framework for tracking and comparing model metrics across different pipeline executions.

B1. Using Vertex AI Pipelines, add a component to divide the data into training and evaluation sets,

This option is incomplete but shares the initial step with A. The general intent of Vertex AI Pipelines is for orchestration, aligning with the need for comparison across executions.

C1. In BigQuery ML, use the CREATE MODEL statement with BOOSTED_TREE_CLASSIFIER as

BigQuery ML's `CREATE MODEL` statement simplifies model creation but offers less granular control for custom feature engineering steps and model comparison across explicit pipeline runs, which is a key requirement.

D1. In BigQuery ML, use the CREATE MODEL statement with BOOSTED_TREE_CLASSIFIER as

Similar to C, BigQuery ML primarily focuses on in-database model training and evaluation, lacking the flexible orchestration and explicit model comparison capabilities of Vertex AI Pipelines.

Concept tested: Vertex AI Pipelines for ML workflow orchestration

Source: https://cloud.google.com/vertex-ai/docs/pipelines/introduction

Topics

#Vertex AI Pipelines#MLOps#Experiment Tracking#Data Preprocessing

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice