As machine learning continues to gain prominence, transparency and explainability are increasingly critical. Without an understanding of these models, they can replicate and worsen human bias, adversely affecting marginalized communities. Algorithmic recourse emerges as a tool for clarifying decisions made by predictive models, providing actionable insights to alter outcomes. They answer, “What do I have to change?” to achieve the desired result. Despite their importance, current algorithmic recourse methods treat all domain values equally, which is unrealistic in real-world settings. While algorithmic recourse is extensively studied in classification tasks, its application to regression tasks remain scarce. In this paper, we propose a novel framework, Relevance-Aware Algorithmic Recourse (RAAR), that leverages the concept of relevance in applying algorithmic recourse to regression tasks. Relevance can supplement other algorithmic recourse methods, but we focus on Bayesian optimization-based methods as a baseline in this paper. We conducted multiple experiments on 15 datasets to outline how relevance influences recourses. Results demonstrate that our approach is comparable to well-known baselines while achieving greater efficiency, measured by shorter computation times and fewer iterations, and lower relative costs, indicated by more minor modifications required to achieve desired outcomes. The results, datasets, and code for replicating this study are available on GitHub.