Multi-agent Algorithmic Recourse Over Time
Published:
This project studies the importance of time in the reliability of algorithmic recourse. We highlight the lack of reliability in recourse recommendations over several competitive settings, potentially setting misguided expectations that could result in detrimental outcomes. These findings emphasize the importance of meticulous consideration when AI systems offer guidance in dynamic environments. Our paper, "Setting the Right Expectations: Algorithmic Recourse Over Time", won the Best AI Track Paper award at EAAMO’23! 
Project members
- João Fonseca (NOVA Information Management School)
- Andrew Bell (New York University)
- Carlo Abrate (CENTAI)
- Francesco Bonchi (CENTAI & Eurecat)
- Julia Stoyanovich (New York University)
Resources
- Project’s GitHub repo
- Publication #1 & Paper Overview (Setting the right expectations: Algorithmic recourse over time)
- Publication #2
- Publication #3 – Under submission!