The remarkable success of Artificial Intelligence in advancing automated decision-making is evident both in academia and industry. Within the plethora of applications, ranking systems hold significant importance in various domains. This paper advocates for the application of a specific form of Explainable AI -- namely, contrastive explanations -- as particularly well-suited for addressing ranking problems. This approach is especially potent when combined with an Evaluative AI methodology, which conscientiously evaluates both positive and negative aspects influencing a potential ranking. Therefore, the present work introduces Evaluative Item-Contrastive Explanations tailored for ranking systems and illustrates its application and characteristics through an experiment conducted on publicly available data.
@article{arxiv.2312.10094,
title = {Evaluative Item-Contrastive Explanations in Rankings},
author = {Alessandro Castelnovo and Riccardo Crupi and Nicolò Mombelli and Gabriele Nanino and Daniele Regoli},
journal= {arXiv preprint arXiv:2312.10094},
year = {2023}
}