Transformative Impact of Data Diversity and Machine Learning on Supply Chain Management

The increasing digitization of global commerce has established Supply Chain Management (SCM) as a critical domain, where leveraging data diversity and advanced analytics is paramount for operational success. This study aims to systematically investigate the transformative impact of varied data sources and machine learning technologies on modern SCM. The focus is on how datasets from sectors like healthcare, e-commerce, and manufacturing, when analyzed with predictive techniques, enhance supply chain resilience and efficiency. A systematic literature review was conducted by selecting and analyzing peer-reviewed articles from the Scopus database published between 2021 and 2025. The findings reveal that while machine learning significantly improves predictive accuracy and enables more adaptive decision-making, the practical applicability of research is often constrained by significant limitations. These include narrow data scope, dependence on secondary or simulated data, and a pronounced regional focus, which collectively hinder the generalizability of insights. Consequently, this review concludes that realizing the full potential of data-driven SCM requires a concerted effort to overcome challenges in data integration and accessibility. This research provides a structured overview of the current landscape and offers a clear direction for developing more robust and globally relevant SCM solutions.