Question-37: Product recommendation in Machine Learning refers to the task of recommending product(s) to a customer based on his purchase history. A product recommender system is an ML model which suggests some items, content or services that a specific user would like to buy or indulge in. Your customer runs a web service used by e-commerce sites to offer product recommendations to users. The company has begun experimenting with a machine learning model on Google Cloud Platform to improve the quality of results. What should the customer do to improve their model's results over time?
A. Export Cloud Machine Learning Engine performance metrics from Stackdriver to BigQuery for analysis of the model's efficacy.
B. Create a plan for migrating the training of machine learning models from Cloud GPUs to Cloud TPUs, which provide superior outcomes.
C. Monitor Compute Engine news on the availability of newer CPU architectures, and deploy the model to them as soon as they become available for enhanced performance.
D. Save a record of past suggestions and their outcomes in BigQuery for use as training data.
Correct Answer
Get All 340 Questions and Answer for Google Professional Cloud Architect
: 4 Explanation: Build a roadmap to move the ML model training from Cloud GPUs to Cloud TPUs which offer better result. This Q for basic understanding of Cloud TPU: https://cloud.google.com/tpu/ Cloud TPU is the custom-designed machine learning ASIC that powers Google products like Translate, Photos, Search, Assistant, and Gmail. Here’s how you can put the TPU and machine learning to work accelerating your company’s success, especially at scale. Read blog about Cloud TPUs: Option-2 just make your training time faster, but doesn't mean increase your model quality (increase accuracy, reduce error). D. adding more data is very useful to increasing the quality of the recommendation model. Option-4 Save a history of recommendations and results of the recommendations in BigQuery, to be used as training data.