SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator

TL;DR

SurvBeX introduces a novel explanation method for machine learning survival models using a modified Beran estimator as a surrogate, enabling interpretation of black-box predictions through local survival function approximations.

Contribution

The paper proposes SurvBeX, a new local explanation technique for survival models that leverages the Beran estimator to interpret black-box predictions.

Findings

SurvBeX effectively interprets survival model predictions.

The method outperforms SurvLIME and SurvSHAP in experiments.

Code for SurvBeX is publicly available.

Abstract

An explanation method called SurvBeX is proposed to interpret predictions of the machine learning survival black-box models. The main idea behind the method is to use the modified Beran estimator as the surrogate explanation model. Coefficients, incorporated into Beran estimator, can be regarded as values of the feature impacts on the black-box model prediction. Following the well-known LIME method, many points are generated in a local area around an example of interest. For every generated example, the survival function of the black-box model is computed, and the survival function of the surrogate model (the Beran estimator) is constructed as a function of the explanation coefficients. In order to find the explanation coefficients, it is proposed to minimize the mean distance between the survival functions of the black-box model and the Beran estimator produced by the generated examples. Many numerical experiments with synthetic and real survival data demonstrate the SurvBeX efficiency and compare the method with the well-known method SurvLIME. The method is also compared with the method SurvSHAP. The code implementing SurvBeX is available at: https://github.com/DanilaEremenko/SurvBeX