What Can I Do Now? Guiding Users in a World of Automated Decisions
This work addresses the issue of lack of user agency in automated decisions, offering a practical tool for applicants to influence outcomes, though it is incremental as it builds on evasion attack formalizations.
The paper tackles the problem of automated decision-making systems by proposing a method to provide applicants with actionable alternatives that would change the algorithm's decision, specifically implemented for decision forests to enumerate subspaces where the classifier outputs a desired result.
More and more processes governing our lives use in some part an automatic decision step, where -- based on a feature vector derived from an applicant -- an algorithm has the decision power over the final outcome. Here we present a simple idea which gives some of the power back to the applicant by providing her with alternatives which would make the decision algorithm decide differently. It is based on a formalization reminiscent of methods used for evasion attacks, and consists in enumerating the subspaces where the classifiers decides the desired output. This has been implemented for the specific case of decision forests (ensemble methods based on decision trees), mapping the problem to an iterative version of enumerating $k$-cliques.