Fairness in decision-making processes is a critical concern across various domains, such as hiring, lending, and resource allocation. Optimal Transport Theory provides a robust mathematical framework to address fairness by modeling the redistribution of resources or outcomes while minimizing the cost of transformation. This paper explores the application of Optimal Transport Theory to achieve fairness by rebalancing biased outcomes to align with equitable distributions. By leveraging Wasserstein distance and related measures, this approach ensures that transformations preserve key structural properties while satisfying fairness constraints. We present computational strategies for implementing fairness-aware transformations and evaluate their effectiveness using real-world datasets. The results demonstrate that Optimal Transport-based methods achieve fairer outcomes without significant trade-offs in utility or efficiency, offering a promising tool for advancing fairness in automated decision systems.