A retail organization uses an AI model to forecast inventory based on customer purchasing trends and updates the model quarterly. The model recently failed to recognize a surge in demand during a…

Question

Options

• ALimited data set diversity impacting model training
• BData drift impacting system forecasting
• COverfitting issues due to a small training data set
• DLack of outlier checks in data affecting forecast accuracy

• A
  8% (2)
• B
  84% (21)
• C
  4% (1)
• D
  4% (1)

Explanation

Data drift occurs when the statistical properties of the real-world data change over time, causing a model's predictions to degrade. In this case, the model was trained on historical purchasing trends that did not reflect the surge in demand during the shopping season. Because the model is only updated quarterly, it could not adapt to the sudden shift in consumer behavior, making data drift the most accurate diagnosis. The other options are plausible but less precise: limited data diversity (A) would typically cause chronic failures, not seasonal ones; overfitting (C) relates to memorizing training data rather than generalizing; and outlier checks (D) are a data quality concern, not the root cause of a seasonal forecasting failure.

No community discussion yet for this question.