A Transparent and Fair AI Tool for Candidate Screening with Simulated Human Oversight

Tommaso Perniola  •  Armando Renzullo  •  Cosimo Russo
abstract

This project aims to develop an AI-based system to assist in job candidate screening,
with a strong focus on ethical concerns such as fairness, transparency, and human
oversight. Modern automated hiring systems risk perpetuating bias and discrimi-
nation if not carefully designed. Our solution leverages machine learning to rank
candidates based on resume data while integrating fairness-aware algorithms to
mitigate potential biases. Human oversight is simulated through a set of predefined
rules that emulate ethical judgment and intervention. The system also incorporates
explainable AI tools to enhance interpretability and trustworthiness. Although real
human reviewers are not part of the loop, the simulation allows us to explore how
human input could improve or correct algorithmic decisions.

outcomes