English

Identifying Biased Subgroups in Ranking and Classification

Machine Learning 2021-08-18 v1 Computers and Society Information Retrieval

Abstract

When analyzing the behavior of machine learning algorithms, it is important to identify specific data subgroups for which the considered algorithm shows different performance with respect to the entire dataset. The intervention of domain experts is normally required to identify relevant attributes that define these subgroups. We introduce the notion of divergence to measure this performance difference and we exploit it in the context of (i) classification models and (ii) ranking applications to automatically detect data subgroups showing a significant deviation in their behavior. Furthermore, we quantify the contribution of all attributes in the data subgroup to the divergent behavior by means of Shapley values, thus allowing the identification of the most impacting attributes.

Keywords

Cite

@article{arxiv.2108.07450,
  title  = {Identifying Biased Subgroups in Ranking and Classification},
  author = {Eliana Pastor and Luca de Alfaro and Elena Baralis},
  journal= {arXiv preprint arXiv:2108.07450},
  year   = {2021}
}

Comments

5 pages

R2 v1 2026-06-24T05:10:35.927Z