Benchmarking and survey of explanation methods for black box models

• Published in: Data mining and knowledge discovery Vol. 37; no. 5; pp. 1719 - 1778
• Main Authors: Bodria, Francesco, Giannotti, Fosca, Guidotti, Riccardo, Naretto, Francesca, Pedreschi, Dino, Rinzivillo, Salvatore
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2023; Springer Nature B.V
• Subjects: Academic Surveys and Tutorials; Art exhibits; Artificial Intelligence; Black boxes; Chemistry and Earth Sciences; Computer Science; Data Mining and Knowledge Discovery; Decision making; Ethics; Information Storage and Retrieval; Machine learning; Mathematical models; Physics; Special Issue on Explainable and Interpretable Machine Learning and Data Mining; Statistics for Engineering; Trust; Explainable artificial intelligence; Interpretable machine learning; Benchmarking; Transparent models
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-023-00933-9

The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.