Google Professional Machine Learning Engineer Question 102
Select 3Google Cloud PlatformYou are tasked with designing a machine learning solution on Google Cloud for a company that wants to build a recommendation system for an e-commerce platform. The platform collects multiple types of data: user purchase history (tabular data), product descriptions (text data), product images (image data), and user reviews (text data). Which practices should you follow to organize this data effectively for training your model?
- A
Store tabular data in BigQuery and use SQL to preprocess and join datasets as needed.
- B
Store product descriptions and user reviews in Cloud Natural Language API for direct model training.
- C
Store image data in Cloud Storage and preprocess using Vertex AI Pipelines or custom scripts.
- D
Use a centralized schema or metadata system to maintain relationships between tabular, text, and image data.
- E
Convert all data types into tabular format to simplify the training process.
Show answer and explanation
Correct answers: A, C, D
Explanation
Organizing different types of data for machine learning requires leveraging appropriate Google Cloud services that are best suited for each data type. Tabular data is best managed in BigQuery, image data should be stored and preprocessed using Cloud Storage and Vertex AI Pipelines, and a centralized schema ensures consistent relationships between data types. Using the right tools and maintaining proper organization allows for efficient model training and deployment.
- A. Correct.
BigQuery is a powerful and scalable solution for managing tabular data. Using SQL for data preprocessing and joining datasets ensures the data is well-organized and ready for training.
- B. Incorrect.
Cloud Natural Language API is primarily used for natural language processing tasks, not for directly storing or training models with text data. Text data should be preprocessed and stored in a format suitable for model training.
- C. Correct.
Cloud Storage is a recommended solution for storing large-scale image data. Preprocessing images via Vertex AI Pipelines or custom scripts ensures the data is prepared in a format suitable for training.
- D. Correct.
Maintaining a centralized schema or metadata system helps ensure relationships between different data types (e.g., linking product images to descriptions) are consistent and accessible during training.
- E. Incorrect.
Converting all data into tabular format is not practical or efficient, as it may lead to loss of important information, especially for unstructured data types like images or text.