Revealing Consumer Preferences in the Fashion Industry Using K-Means Clustering

Abstract

The fashion industry, driven by rapidly shifting e-commerce trends and consumer preferences, demands precise data analysis to optimize marketing strategies and enhance customer satisfaction. This study utilizes data mining techniques, specifically K-Means Clustering and the Elbow Method, to reveal consumer preferences within a dataset of 1,000 fashion product sales records, which include attributes such as product ID, name, brand, category, price, rating, color, and size. By grouping data into distinct clusters based on price and rating preferences, the analysis uncovers four key consumer segments. The optimal number of clusters is confirmed using the WCSS (Within-Cluster Sum of Square) method. These insights offer valuable guidance for refining marketing strategies in the fashion industry. Future research should consider additional variables and employ advanced tools for deeper analysis.