# What Can I Do Now? Guiding Users in a World of Automated Decisions

## TL;DR

This paper introduces a method to empower users by providing alternative inputs that could change automated decision outcomes, using a formal approach inspired by evasion attack techniques for decision forests.

## Contribution

It presents a novel approach to identify input modifications that alter automated decisions, specifically applied to decision forests, enhancing user agency in automated decision processes.

## Key findings

- Method effectively finds alternative inputs for decision change
- Applicable to decision forests and similar ensemble models
- Provides a formal framework for user empowerment in automated decisions

## Abstract

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.