AWS Certified Machine Learning – Specialty — Question 36

A Machine Learning Specialist deployed a model that provides product recommendations on a company's website. Initially, the model was performing very well and resulted in customers buying more products on average. However, within the past few months, the Specialist has noticed that the effect of product recommendations has diminished and customers are starting to return to their original habits of spending less. The Specialist is unsure of what happened, as the model has not changed from its initial deployment over a year ago.
Which method should the Specialist try to improve model performance?

Answer options

• A. The model needs to be completely re-engineered because it is unable to handle product inventory changes.
• B. The model's hyperparameters should be periodically updated to prevent drift.
• C. The model should be periodically retrained from scratch using the original data while adding a regularization term to handle product inventory changes
• D. The model should be periodically retrained using the original training data plus new data as product inventory changes.

Correct answer: D

Explanation

The correct answer is D because periodically retraining the model with both original and new data allows it to adapt to changes in customer behavior and product inventory. Option A suggests a complete redesign, which is unnecessary; option B focuses solely on hyperparameter tuning, which may not address the root cause; and option C implies starting from scratch, which is less efficient than incorporating new data.