Integration of data science and big data analytics offers unparalleled opportunities in sustainability initiatives at this juncture. The study adopts a mixed-methods approach, combining the systematic literature review of 127 peer-reviewed articles between 2022 and 2024 and case study analyses of 15 successful sustainability projects across three continents. The analysis showcased the following three main findings: Machine learning algorithms applied to environmental sensor data can predict patterns of degradation with 89% accuracy, allowing for appropriate interventions; big data analytics and integration with IoT devices cut energy consumption in a smart city by nearly 23%; frameworks for real-time data processing can boost efficiency in the allocation of resources for sustainable agriculture practices by around 34%. The results have shown that data-driven decision-making strongly enhances sustainability outcomes, especially with the establishment of robust data governance frameworks that promote cross-sector collaboration. Concluded that while data science applications toward sustainability hold much promise, their successful execution depends on how to attain a technological approach with equal emphasis on environmental concerns and social equity. This study thus provides a comprehensive framework to effectively implement data-driven sustainability initiatives for organizations and policymakers.