During an AI model audit, the auditor discovers that the model's predictions are disproportionately influenced by a single feature that accounts for 68% of total SHAP value contribution. What risk does this finding indicate?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because a model dominated by a single feature is brittle: if that feature becomes unavailable, its measurement changes, or it begins to carry bias, the model's entire output is affected. This concentration risk means the model's performance and fairness hinge on one data point's integrity.
Full explanation below image
Full Explanation
B is correct because a model dominated by a single feature is brittle: if that feature becomes unavailable, its measurement changes, or it begins to carry bias, the model's entire output is affected. This concentration risk means the model's performance and fairness hinge on one data point's integrity. This finding also raises questions about whether the model has truly learned the underlying problem or is exploiting a shortcut. Overfitting (A) is a different problem. An irrelevant feature (C) would typically receive low SHAP values, not dominate them. No blanket prohibition exists on models with dominant features (D); this is a risk management concern, not a regulatory rule.