The increasing complexity of transactional data in supermarket operations necessitates robust analytical methods to enhance product management and strategic decision-making. This study proposes a combined approach using the K-Means clustering algorithm and the Analytic Hierarchy Process (AHP) to segment products based on financial performance metrics. K-Means is employed to group products according to key indicators, including margin, profit, loss value, and revenue. Subsequently, AHP is used to assign relative weights to these variables and to calculate a composite score for each cluster, providing a strategic evaluation framework. The integration of these methods allows for the identification of product groupings with distinct financial profiles. Among the three resulting clusters, Cluster 1 achieved the highest strategic value, with an AHP score of 21.540, supported by the highest average margin (44.00), profit (1.540), and the lowest loss value (0.561). Average revenue across all clusters ranged from 3.500 to 3.637, with total AHP scores summing to 60.700. This methodological framework offers retail decision-makers a data-driven tool to prioritize products for promotion, shelf placement, and inventory control. Furthermore, the approach demonstrates potential applicability in other retail environments with similar data characteristics.
Copyrights © 2026