Professional Data EngineerOperationalizing machine learning modelsHard
A global e-commerce company is developing a machine learning model to detect fraudulent transactions. They need to ensure that the entire ML lifecycle—from data preparation and model training to deployment and monitoring—is automated, repeatable, and scalable across different regions. The solution must support various ML frameworks and allow for custom code execution within the pipeline steps. Which Google Cloud service is most suitable for building this automated MLOps pipeline?
- ACloud Functions
- BVertex AI Pipelines
- CCloud Build
- DCloud Dataflow
Show answer & explanationAnswer & explanation
Correct answer: B. Vertex AI Pipelines
Vertex AI Pipelines, based on Kubeflow Pipelines, is specifically designed for building, deploying, and managing robust, repeatable, and scalable MLOps pipelines on Google Cloud, supporting custom components and various ML frameworks.
Why the other options are wrong
- A. Cloud Functions are serverless compute services for individual event-driven functions, not for orchestrating complex, multi-stage ML pipelines.
- C. Cloud Build is a CI/CD service primarily for building and deploying software, while it can trigger ML pipeline steps, it's not a full MLOps orchestrator like Vertex AI Pipelines.
- D. Cloud Dataflow is for batch and stream data processing, not for orchestrating the entire ML lifecycle including training and deployment.
Vertex AI Pipelines
A serverless MLOps platform on Google Cloud for orchestrating and automating end-to-end machine learning workflows, based on Kubeflow Pipelines.
- Enables repeatable and scalable ML pipelines.
- Manages dependencies and resource allocation.
- Supports custom components and various ML frameworks.
Memory trick: Pipeline your ML, automate the whole flow.