An IS auditor notes that an AI model achieved significantly better results on training data than on test data. Which of the following problems with the model has the IS auditor identified?

The correct answer is B. Overfitting. Overfitting occurs when a model learns the training data too well - including its noise and idiosyncrasies - and therefore performs significantly better on training data than on unseen test data. The large gap in performance between training and test results is the classic hallma

AI Risk Management and Controls

Question

Options

AUnderfitting
BOverfitting
CGeneralization
DBias

How the community answered

(43 responses)

A
5% (2)
B
93% (40)
D
2% (1)

Explanation

Overfitting occurs when a model learns the training data too well - including its noise and idiosyncrasies - and therefore performs significantly better on training data than on unseen test data. The large gap in performance between training and test results is the classic hallmark of overfitting. Underfitting (A) is the opposite: the model performs poorly on both training and test data. Generalization (C) refers to how well a model applies to new data - overfitting is a failure of generalization, not a distinct problem category in this context. Bias (D) refers to systematic errors, not the training-vs-test performance gap.

Topics

#Overfitting#Model evaluation#Generalization#AI model risks

Community Discussion

No community discussion yet for this question.

Full AAIA Practice