QuestionQ26

VerifiedML Model Development

An ML engineer is building a fraud detection model on AWS. The training dataset includes transaction logs, customer profiles, and tables from an on-premises MySQL database. The transaction logs and customer profiles are stored in Amazon S3.

The dataset has a class imbalance that affects how the model's algorithm learns. In addition, many of the features are interdependent. The algorithm is not capturing all of the desired underlying patterns in the data.

The ML engineer must use an Amazon SageMaker built-in algorithm to train the model.

Which algorithm should the ML engineer use to satisfy this requirement?

Explanation

Amazon SageMaker LightGBM is a built-in supervised tabular classification algorithm based on gradient-boosted decision trees. It can address binary class imbalance through the is_unbalance or scale_pos_weight hyperparameters, and its tree-based model learns nonlinear relationships and interactions among features. AWS LightGBM hyperparameters

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!