# Algorithmic recourse in sequential decision-making for long-term fairness

## TL;DR

This paper introduces a new framework for achieving long-term fairness in sequential decisions by allowing individuals to take actionable steps to improve their outcomes over time.

## Contribution

The novel contribution is the introduction of SCARF, a causally grounded framework for sequential algorithmic recourse that balances short-term and long-term fairness.

## Key findings

- SCARF generates temporally coherent recourse plans that reduce disparities over multiple decision cycles.
- Experiments show that SCARF effectively balances trade-offs between short-term and long-term fairness.
- The framework is practical for analyzing fairness dynamics in dynamic decision-making.

## Abstract

Long-term fairness in sequential decision-making is critical yet challenging, as decisions at each time step influence future opportunities and outcomes, potentially exacerbating existing disparities over time. While existing methods primarily achieve fairness by directly adjusting decision models, in this work, we study a complementary perspective based on sequential algorithmic recourse, in which fairness is pursued through actionable interventions for individuals. We introduce Sequential Causal Algorithmic Recourse for Fairness (SCARF), a causally grounded framework that generates temporally coherent recourse trajectories by integrating structural causal modeling with sequential generative modeling. By explicitly incorporating both short-term and long-term fairness constraints, as well as practical budget limitations, SCARF generates personalized recourse plans that effectively mitigate disparities over multiple decision cycles. Through experiments on synthetic and semi-synthetic datasets, we empirically examine how different recourse strategies influence fairness dynamics over time, illustrating the trade-offs between short-term and long-term fairness under sequential interventions. The results demonstrate that SCARF provides a practical and informative framework for analyzing long-term fairness in dynamic decision-making settings.