Exam Professional Cloud Architect topic 1 question 92 discussion

Model performance is generally based on the volume of its training data input. The more the data, the better the model.

A,B,C is defining about the performance of ML but not the result....only the training data will give good ML result/predictions

Best answer is D. Other 3 makes no sense

Need to improve the model results and not performance .. hence D

Answer is D

Model performance is generally based on the volume of its training data input. The more the data, the better the model.

The following insights and recommendations can be exported (to bigquery): IAM recommender VM machine type recommender Managed instance group machine type recommender Idle PD recommender Idle VM recommender Cloud SQL overprovisioned instance recommender Cloud SQL idle instance recommender Unattended project recommender Cloud Run Service Identity recommender https://cloud.google.com/recommender/docs/bq-export/export-recommendations-to-bq None of this is correlated with Machine Learning, how can be D? looks more A the answer

i vote D

D. Save a history of recommendations and results of the recommendations in BigQuery, to be used as training data.

"training data" is the key in option "D" and that's the answer

D seems to be the correct answer