Advanced Customer Segmentation in the Natural Supplements Industry to Enhance Marketing Strategies Using Big Data Tools

This study underscores the critical role of Big Data and Business Intelligence tools in modern corporate decision-making, particularly in the natural supplements industry, where understanding customer behavior through advanced segmentation can significantly enhance marketing strategies and overall business performance. In this research, two years of purchase records from a company in the natural supplements industry were analyzed using a combination of segmentation algorithms and RFM (Recency, Frequency, and Monetary value) analysis to identify distinct customer profiles. Leveraging Python, three clustering algorithms—K-means, DBSCAN, and Agglomerative Hierarchical—were implemented and evaluated, with the Silhouette Score identifying K-means as the most effective approach. This model categorized customers into four key segments: high-value customers, potential growth customers, at-risk customers, and occasional buyers. The insights derived from this segmentation process were fundamental in designing targeted marketing strategies, optimizing resource allocation, and improving customer retention. Furthermore, this study highlights how businesses that embrace data-driven decision-making gain a competitive edge by personalizing customer interactions, enhancing efficiency, and increasing the return on investment in marketing. The findings suggest that the integration of predictive modeling and intelligent data analysis supports more precise segmentation and enables organizations to anticipate trends, mitigate risks, and drive sustainable growth. The application of Big Data and Business Intelligence in this context allows companies to transform large datasets into actionable insights, fostering proactive and informed decision-making in dynamic and competitive markets. Ultimately, this research provides strong evidence that leveraging advanced analytics can lead to substantial economic benefits, positioning businesses for long-term success in data-driven environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.