Print Email Facebook Twitter The endogenous dynamics induced by Algorithmic Recourse Title The endogenous dynamics induced by Algorithmic Recourse Author Angela, Giovan (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 Machine learning classifiers have become a household tool for banks, companies, and government institutes for automated decision-making. In order to help explain why a person was classified a certain way, a solution was proposed that could generate these counterfactual explanations. Several generators have been introduced and tested but include several side effects. One of these side effects is making it easier to be classified incorrectly after sufficient recourse has been applied. Dynamics, a.k.a. shifts in both the domain and model, cause these side effects. We aimed to quantify these dynamics induced by two generators, Wachter et al. and REVISE, and compare them against each other. We performed three experiments with both generators and looked at the effect a different dataset, model, or hyper-parameter may have had on the dynamics. We found that REVISE induces a slight model shift while the domain shifts increase with each round of recourse. Subject dynamicsalgorithmic recourseREVISE To reference this document use: http://resolver.tudelft.nl/uuid:442d5ac1-9bdc-4b09-b9cb-a583365e18f6 Part of collection Student theses Document type bachelor thesis Rights © 2022 Giovan Angela Files PDF The_endogenous_dynamics_i ... course.pdf 2.27 MB Close viewer /islandora/object/uuid:442d5ac1-9bdc-4b09-b9cb-a583365e18f6/datastream/OBJ/view