Retail supply chains generate huge volumes of data that can provide valuable insights if analyzed effectively. This paper explores how retailers can leverage Big Data analytics techniques on supply chain data to gain enhanced visibility into their operations. We examine three use cases of data-driven supply chain visibility: (1) predictive replenishment to anticipate future demand and optimize inventory levels; (2) personalized assortment optimization to tailor product selections for local customer segments; and (3) optimized order fulfillment to improve delivery times and reduce transportation costs. We analyze how retailers can apply machine learning algorithms and statistical analysis on point-of-sale data, inventory data, customer data, and external data sources to uncover hidden patterns and drive data-driven decisions in these areas. The results include reduced excess inventory, fewer stock-outs, higher in-store product availability, lower fulfillment costs, and improved customer experience. Data-driven supply chain visibility allows retailers to transition from a reactive, speculative business model to a predictive, personalized model that enhances competitiveness. This study investigates the role of big data analytics to improve supply chain visibility in the retail industry through providing significant benefits in sustainable SCM, including enhanced visibility, improved decision-making and increased efficiency, which can lead to improved environmental and social performance. By applying appropriate preprocessing techniques and using prediction models such as Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing, and others, organizations can gain insights into sales patterns and trends, optimize inventory levels, and improve supply chain efficiency and customer satisfaction. Our findings recommend that organizations seeking to leverage Big Data Analytics in their SCM practices should prioritize data quality, analytical capabilities, and stakeholder collaboration. Finally, we found that visualizing sales distribution based on different criteria can be a useful tool in exploratory data analysis, enabling organizations to gain insights into sales patterns and trends that may not be apparent from the raw data.