Best Practices for Enhancing Model Performance
Question
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?
Answers
Explanations
Click on the arrows to vote for the correct answer
A. B. C. D.D.
The correct answer is D. Save a history of recommendations and results of the recommendations in BigQuery, to be used as training data.
Explanation: To improve the results of a machine learning model over time, it is important to continuously train the model with new data. Saving a history of recommendations and results in BigQuery allows the customer to collect this data and use it as training data to continuously improve the model. The more data the model is trained on, the more accurate it will become.
Option A, exporting Cloud Machine Learning Engine performance metrics from Stackdriver to BigQuery, is useful for analyzing the efficiency of the model, but it does not directly improve the model's results over time.
Option B, building a roadmap to move the machine learning model training from Cloud GPUs to Cloud TPUs, may offer better results, but it is not a guaranteed solution. It may require significant changes to the machine learning model and may not necessarily improve the accuracy of the model.
Option C, monitoring Compute Engine announcements for availability of newer CPU architectures and deploying the model to them as soon as they are available for additional performance, is also not a guaranteed solution to improve the model's accuracy. It may require significant changes to the machine learning model and may not necessarily improve the accuracy of the model.
Therefore, option D is the best approach for continuously improving the machine learning model's accuracy over time.
