MLS-C01 · Question #176
A bank wants to launch a low-rate credit promotion. The bank is located in a town that recently experienced economic hardship. Only some of the bank's customers were affected by the crisis, so the…
The correct answer is B. Use Amazon SageMaker Studio to rebuild the model. The truncated question text indicates the credit team is struggling to interpret the model's decisions - a classic explainability problem. Option B involves using Amazon SageMaker Studio with Amazon SageMaker Clarify to add model explainability to the existing XGBoost model…
Question
A bank wants to launch a low-rate credit promotion. The bank is located in a town that recently experienced economic hardship. Only some of the bank's customers were affected by the crisis, so the bank's credit team must identify which customers to target with the promotion. However, the credit team wants to make sure that loyal customers' full credit history is considered when the decision is made. The bank's data science team developed a model that classifies account transactions and understands credit eligibility. The data science team used the XGBoost algorithm to train the model. The team used 7 years of bank transaction historical data for training and hyperparameter tuning over the course of several days. The accuracy of the model is sufficient, but the credit team is struggling to explain accurately why the model denies credit to some customers. The credit team has almost no skill in data science. What should the data science team do to address this issue in the MOST operationally efficient manner?
Options
- AUse Amazon SageMaker Studio to rebuild the model.
- BUse Amazon SageMaker Studio to rebuild the model.
- CCreate an Amazon SageMaker notebook instance. Use the notebook instance and the XGBoost
- DUse Amazon SageMaker Studio to rebuild the model.
How the community answered
(25 responses)- A16% (4)
- B72% (18)
- C4% (1)
- D8% (2)
Explanation
The truncated question text indicates the credit team is struggling to interpret the model's decisions - a classic explainability problem. Option B involves using Amazon SageMaker Studio with Amazon SageMaker Clarify to add model explainability to the existing XGBoost model. SageMaker Clarify computes SHAP (SHapley Additive exPlanations) values, which show the contribution of each feature (e.g., transaction history, account age) to individual predictions. This lets the credit team understand why a specific customer was or was not recommended for the promotion, which is essential for regulatory compliance in financial services. Rebuilding the model as a different algorithm type would sacrifice the accuracy achieved after days of hyperparameter tuning. The key insight is that the problem is not model performance but model interpretability, and SageMaker Clarify addresses this without requiring retraining.
Topics
Community Discussion
No community discussion yet for this question.