Quantifying the Endogenous Domain and Model Shifts Induced by the CLUE Recourse Generator

Quantifying the Endogenous Domain and Model Shifts Induced by the CLUE Recourse Generator

Dobiczek, Karol (TU Delft Electrical Engineering, Mathematics and Computer Science)

Liem, C.C.S. (mentor)
Altmeyer, P. (mentor)
Migut, M.A. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2022-06-23

Employing counterfactual explanations in a recourse process gives a positive outcome to an individual, but it also shifts their corresponding data point. For systems where models are updated frequently, a change might be seen when recourse is applied, and after multiple rounds, severe shifts in both model and domain may occur. Algorithmic recourse frameworks such as CARLA compare the counterfactual generators based on the effectiveness and cost of employing recourse, but little to no previous work has been done on analyzing the shifts in dynamics of the systems. In this paper, we propose a set of metrics aimed at measuring shifts in the domains and models employed in those systems, as well as an experiment framework built on top of CARLA. These metrics allow us to analyze experimentally the characteristics of shifts in dynamics induced by the CLUE and Wachter generators.

counterfactual explanations
algorithmic recourse
CLUE
explainable artificial intelligence
domain shift
model shift
machine learning
black-box algorithms

http://resolver.tudelft.nl/uuid:6a249d72-9e1e-4e81-abdc-463260c7d1bc

Student theses

bachelor thesis

© 2022 Karol Dobiczek