Which AI model is BEST suited to ensure explainability in an HR department's pre-screening tool for candidate resumes?

The correct answer is C. Decision tree. Decision trees are inherently interpretable (white-box) models: each prediction follows a clear, traceable path of if/then rules that a human can read and audit. This is essential in HR pre-screening, where explainability is required to justify hiring decisions and comply with…

AI Security Design and Implementation

Question

Options

ASupport vector machine
BNeural network
CDecision tree
DGradient boosting machine

How the community answered

(33 responses)

A
3% (1)
B
6% (2)
C
82% (27)
D
9% (3)

Explanation

Decision trees are inherently interpretable (white-box) models: each prediction follows a clear, traceable path of if/then rules that a human can read and audit. This is essential in HR pre-screening, where explainability is required to justify hiring decisions and comply with anti-discrimination regulations (e.g., EEOC guidelines). Neural networks (B) are black-box models with low interpretability. Support vector machines (A) have limited explainability, especially with non-linear kernels. Gradient boosting machines (D) are ensembles of trees that sacrifice interpretability for accuracy, making individual decision paths difficult to explain.

Topics

#AI Explainability#Machine Learning Models#Decision Trees#Responsible AI

Community Discussion

No community discussion yet for this question.

Full AAISM Practice