Visualizing Adidas and Nike Customer Segments Using K-Means Clustering

This study explores the application of the K-Means Clustering algorithm to categorize Adidas and Nike customers based on their behavior and preferences. The analysis was conducted on a dataset of 3,268 products from Adidas and Nike, focusing on grouping customer behavior into actionable segments. The K-Means algorithm identified key features, with Listing Price and Sale Price as significant variables. The Elbow Method determined the optimal number of clusters as three (k=3), and the Silhouette Score confirmed the model's effectiveness. The results show that the K-Means algorithm effectively distinguishes customer segments within the Adidas vs. Nike shoe dataset, represented through scatter plots and silhouette diagrams that reveal well-separated clusters. These findings are valuable for refining marketing and pricing strategies, enabling Adidas and Nike to better target specific customer groups. Future research could enhance these findings by experimenting with additional features, exploring alternative clustering algorithms like hierarchical clustering or DBSCAN, and fine-tuning parameters such as the number of clusters or preprocessing techniques to further optimize results.