Kovalev, M. and Utkin, L. and Coolen, F. and Konstantinov, A. (2022) 'Counterfactual explanation of machine learning survival models.', Informatica, 32 (4). pp. 817-847.
A method for counterfactual explanation of machine learning survival models is proposed. One of the difficulties of solving the counterfactual explanation problem is that the classes of examples are implicitly defined through outcomes of a machine learning survival model in the form of survival functions. A condition that establishes the difference between survival functions of the original example and the counterfactual is introduced. This condition is based on using a distance between mean times to event. It is shown that the counterfactual explanation problem can be reduced to a standard convex optimization problem with linear constraints when the explained black-box model is the Cox model. For other black-box models, it is proposed to apply the wellknown Particle Swarm Optimization algorithm. Numerical experiments with real and synthetic data demonstrate the proposed method.
|Keywords:||interpretable model; explainable AI; survival analysis; censored data; convex optimization; counterfactual explanation; Cox model; Particle Swarm Optimization;|
|Full text:||(AM) Accepted Manuscript|
Download PDF (5685Kb)
|Full text:||(VoR) Version of Record|
Available under License - Creative Commons Attribution 4.0.
Download PDF (2645Kb)
|Publisher Web site:||UNSPECIFIED|
|Publisher statement:||Accepted Manuscript: © [Maxim Kovalev, Lev Utkin, Frank Coolen, Andrei Konstantinov, 2021]. The definitive, peer reviewed and edited version of this article is published in [Informatica, 32, 4, 817-847, 2021, DOI 10.15388/21-INFOR468]. Version of Record: © Vilnius University. This article is Open Access under a Creative Commons Attribution (CC BY) licence http://creativecommons.org/licenses/by/4.0/.|
|Date accepted:||02 December 2021|
|Date deposited:||06 December 2021|
|Date of first online publication:||09 December 2021|
|Date first made open access:||06 December 2021|
Save or Share this output
|Look up in GoogleScholar|