Sales Data Clustering Using the K-Means Algorithm to Determine Retail Product Needs

Sales data is a systematic record of transactional behavior with goods or services distributed over time boundaries and furnishes primary key business metrics for evaluating and planning. Using the K-Means clustering algorithm, this research segments retail product demand by differences attributes to identify demand patterns. The iterative process of clustering ended at the fifth cycle after the division of objects in each cluster stabilized, which can serve as a sign that we arrive at an optimal solution. Results showed that the first cluster located at a centroid 94, 6 contains 100 data items belonging in a primary set and similarly fifth cluster (same centroid) had also same number of products. The automated approach of Collaboratory also differs from the manual method where there are not pre-defined cluster initial values in our preliminary setup. Despite this procedural difference, there is a remarkable concision in the results which demonstrates the strength of the method when implemented using different ingrained constructions. These results offer some refined results on product classification, which is essential to solve the problem that retail ranks may vary during inventory management and sales optimization.