DeepAI AI Chat
Log In Sign Up

Generating personalized counterfactual interventions for algorithmic recourse by eliciting user preferences

by   Giovanni De Toni, et al.
Fondazione Bruno Kessler
Università di Trento
Université Paris-Dauphine

Counterfactual interventions are a powerful tool to explain the decisions of a black-box decision process, and to enable algorithmic recourse. They are a sequence of actions that, if performed by a user, can overturn an unfavourable decision made by an automated decision system. However, most of the current methods provide interventions without considering the user's preferences. For example, a user might prefer doing certain actions with respect to others. In this work, we present the first human-in-the-loop approach to perform algorithmic recourse by eliciting user preferences. We introduce a polynomial procedure to ask choice-set questions which maximize the Expected Utility of Selection (EUS), and use it to iteratively refine our cost estimates in a Bayesian setting. We integrate this preference elicitation strategy into a reinforcement learning agent coupled with Monte Carlo Tree Search for efficient exploration, so as to provide personalized interventions achieving algorithmic recourse. An experimental evaluation on synthetic and real-world datasets shows that a handful of queries allows to achieve a substantial reduction in the cost of interventions with respect to user-independent alternatives.


Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis

Being able to provide counterfactual interventions - sequences of action...

Extracting Incentives from Black-Box Decisions

An algorithmic decision-maker incentivizes people to act in certain ways...

Estimation of Counterfactual Interventions under Uncertainties

Counterfactual analysis is intuitively performed by humans on a daily ba...

Understanding and Shifting Preferences for Battery Electric Vehicles

Identifying personalized interventions for an individual is an important...

'Put the Car on the Stand': SMT-based Oracles for Investigating Decisions

Principled accountability in the aftermath of harms is essential to the ...

On Optimizing Interventions in Shared Autonomy

Shared autonomy refers to approaches for enabling an autonomous agent to...