AWS Certified Machine Learning – Specialty — Question 80

A Data Scientist is training a multilayer perception (MLP) on a dataset with multiple classes. The target class of interest is unique compared to the other classes within the dataset, but it does not achieve and acceptable recall metric. The Data Scientist has already tried varying the number and size of the MLP's hidden layers, which has not significantly improved the results. A solution to improve recall must be implemented as quickly as possible.
Which techniques should be used to meet these requirements?

Answer options

• A. Gather more data using Amazon Mechanical Turk and then retrain
• B. Train an anomaly detection model instead of an MLP
• C. Train an XGBoost model instead of an MLP
• D. Add class weights to the MLP's loss function and then retrain

Correct answer: D

Explanation

Adding class weights to the loss function helps address the class imbalance, thereby improving the recall for the target class. The other options either involve changing the model type or collecting more data, which may take longer and may not directly address the recall issue in the short term.