<![CDATA[This research aims to analyze product segmentation in the apparel industry using the K-Means Clustering algorithm optimized with Particle Swarm Optimization (PSO) to generate accurate product segmentation that can support more effective marketing strategies for a company. The data used in this analysis were obtained from sales transactions of a clothing manufacturing company that offers various categories of apparel products. The dataset consists of 333 rows and includes transaction numbers, product types, quantities sold, and total sales values. The data were processed using the Python programming language via Visual Studio Code. The segmentation process was initially performed using the K-Means algorithm to group products, and the Elbow method was applied to determine the optimal number of clusters. The number of clusters obtained from the Elbow method was then optimized using PSO to find more optimal cluster counts and centroids. Cluster evaluation was conducted by comparing the values of several metrics, including the Davies-Bouldin Index (DBI), Silhouette Score, Sum of Squared Error (SSE), and the SSW/SSB ratio. Although the DBI increased slightly from 0.6690 to 0.6878, indicating greater similarity between clusters, the improvement in the Silhouette Score from 0.5513 to 0.5569 suggests better internal consistency within the clusters. Furthermore, the reduction in SSE from 418.52 to 313.25 indicates a tighter distribution of data within clusters, while the significant decrease in the SSW/SSB ratio from 0.4582 to 0.3075 demonstrates more clearly defined cluster boundaries and improved separation. The results of the study produced four distinct product clusters, enabling the company to implement more targeted and differentiated marketing strategies.]]>
Copyrights © 2025
