MLS-C01 Question #392: Real Exam Question with Answer & Explanation

Question

A data scientist needs to develop a model to detect fraud. The data scientist has less data for fraudulent transactions than for legitimate transactions. The data scientist needs to check for bias in the model before finalizing the model. The data scientist needs to develop the model quickly. Which solution will meet these requirements with the LEAST operational overhead?

Options

• AProcess and reduce bias by using the synthetic minority oversampling technique (SMOTE) in
• BProcess and reduce bias by using the synthetic minority oversampling technique (SMOTE) in
• CProcess and reduce bias by using the synthetic minority oversampling technique (SMOTE) in
• DProcess and reduce bias by using an Amazon SageMaker Studio notebook. Use Amazon

Explanation

SMOTE (Synthetic Minority Oversampling Technique) helps to balance the dataset by oversampling the minority class (fraudulent transactions). Performing SMOTE directly in Amazon SageMaker Studio simplifies the workflow, eliminating the need for an additional service like EMR. Amazon SageMaker JumpStart allows the data scientist to quickly develop the model using pre- built algorithms and templates, reducing the time spent on custom model development. Amazon SageMaker Clarify is specifically designed to check for bias, providing bias detection throughout the model lifecycle, including pre- and post- training phases. It efficiently integrates into SageMaker, minimizing operational effort.

No community discussion yet for this question.