NICE: an algorithm for nearest instance counterfactual explanations

• Published in: Data mining and knowledge discovery Vol. 38; no. 5; pp. 2665 - 2703
• Main Authors: Brughmans, Dieter, Leyman, Pieter, Martens, David
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Chemistry and Earth Sciences; Computer Science; Data Mining and Knowledge Discovery; Information Storage and Retrieval; Optimization; Physics; Search process; Sparsity; Special Issue on Explainable and Interpretable Machine Learning and Data Mining; Statistics for Engineering; XAI; Counterfactual explanations; Machine learning

In this paper we propose a new algorithm, named NICE, to generate counterfactual explanations for tabular data that specifically takes into account algorithmic requirements that often emerge in real-life deployments: (1) the ability to provide an explanation for all predictions, (2) being able to ha...