MLS-C01 Question #199: Real Exam Question with Answer & Explanation

Question

A retail company uses a machine learning (ML) model for daily sales forecasting. The company's brand manager reports that the model has provided inaccurate results for the past 3 weeks. At the end of each day, an AWS Glue job consolidates the input data that is used for the forecasting with the actual daily sales data and the predictions of the model. The AWS Glue job stores the data in Amazon S3. The company's ML team is using an Amazon SageMaker Studio notebook to gain an understanding about the source of the model's inaccuracies. What should the ML team do on the SageMaker Studio notebook to visualize the model's degradation MOST accurately?

Options

• ACreate a histogram of the daily sales over the last 3 weeks. In addition, create a histogram
• BCreate a histogram of the model errors over the last 3 weeks. In addition, create a
• CCreate a line chart with the weekly mean absolute error (MAE) of the model.
• DCreate a scatter plot of daily sales versus model error for the last 3 weeks. In addition,

Explanation

{"question_number": 1, "correct_answer": "C", "explanation": "To visualize model degradation over time, the most accurate approach is a line chart of weekly Mean Absolute Error (MAE). MAE directly measures prediction error (the average absolute difference between predicted and actual sales), and plotting it weekly over 3 weeks reveals whether error is increasing (degradation trend) and at what rate. Histograms of sales or errors show distributions but lose the temporal trend needed to diagnose degradation. A scatter plot of daily sales vs. model error reveals correlation but not the time-series progression of declining performance. The line chart with weekly MAE is the most direct, interpretable visualization for tracking model degradation over time.", "generated_by": "claude-sonnet", "llm_judge_score": 3}

No community discussion yet for this question.