Print Email Facebook Twitter Quantifying the Endogenous Domain and Model Shifts Induced by the DiCE Generator Title Quantifying the Endogenous Domain and Model Shifts Induced by the DiCE Generator Author Buszydlik, Aleksander (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Liem, C.C.S. (mentor) Altmeyer, P. (mentor) Migut, M.A. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-23 Abstract Algorithmic recourse aims to provide individuals affected by a negative classification outcome with actions which, if applied, would flip this outcome. Various approaches to the generation of recourse have been proposed in the literature; these are typically assessed on statistical measures such as the validity of generated explanations or their proximity to the training data. However, little to no attention has been paid to the underlying dynamics of recourse. If a group of individuals applies the suggested actions, they may over time induce a shift in the domain or model. We propose a framework for the measurement of such intrinsic shifts, and conduct an analysis of the dynamics of recourse implemented by the generators proposed by Mothilal et al. and Wachter et al.. Our results suggest that the application of recourse is likely to introduce statistically significant shifts in the system, and that the underlying dataset and model impact the behavior of the generators. Subject algorithmic recoursemachine learningexplainable artificial intelligencecounterfactual explanationsDICEdomain shiftmodel shiftblack box algorithms To reference this document use: http://resolver.tudelft.nl/uuid:cb0bf4ac-4055-489b-b768-e5b53ec6fa47 Part of collection Student theses Document type bachelor thesis Rights © 2022 Aleksander Buszydlik Files PDF Buszydlik_Endogenous_Shif ... h_DICE.pdf 5.36 MB Close viewer /islandora/object/uuid:cb0bf4ac-4055-489b-b768-e5b53ec6fa47/datastream/OBJ/view