AWS Certified Machine Learning – Specialty — Question 336

A machine learning (ML) specialist is building a credit score model for a financial institution. The ML specialist has collected data for the previous 3 years of transactions and third-party metadata that is related to the transactions.

After the ML specialist builds the initial model, the ML specialist discovers that the model has low accuracy for both the training data and the test data. The ML specialist needs to improve the accuracy of the model.

Which solutions will meet this requirement? (Choose two.)

Answer options

• A. Increase the number of passes on the existing training data. Perform more hyperparameter tuning.
• B. Increase the amount of regularization. Use fewer feature combinations.
• C. Add new domain-specific features. Use more complex models.
• D. Use fewer feature combinations. Decrease the number of numeric attribute bins.
• E. Decrease the amount of training data examples. Reduce the number of passes on the existing training data.

Correct answer: A, C

Explanation

Low accuracy on both training and test datasets indicates that the model is underfitting. To address underfitting, the complexity of the model must be increased, which can be achieved by adding domain-specific features, using more complex architectures, training for more passes, or tuning hyperparameters. Reducing the training data, increasing regularization, or simplifying features would further degrade model performance by exacerbating the underfitting issue.