Nguyen, ThanhDumpert, Kora2024-08-302024-08-302024https://hdl.handle.net/1794/2991878 pagesClothing, once a necessity for human survival, has evolved into a powerful means of self-expression and social identification. Today, the fashion industry stands as a multi-trillion-dollar global force, shaping economies and cultures. However, its volatile nature and environmental footprint necessitate innovative approaches to trend identification and inventory management. This research explores the fusion of machine learning techniques with fashion trend analysis to offer an accessible solution. By leveraging image clustering algorithms, this study identifies key patterns and trends within fashion apparel. The research unveils significant insights into Spring/Summer 2024 color preferences, item types, and material/print trends. An example of trends identified include red colors, dresses, and stripes. Notably, the identified trends are cross-referenced with traditional fashion publications to assess accuracy. While the study acknowledges certain limitations, particularly in item type differentiation, it proposes avenues for future research. Ultimately, this research not only offers a glimpse into the future of fashion trend analysis but also presents a pathway towards more sustainable and efficient inventory planning. By harnessing the power of machine learning, the fashion industry can align production with consumer preferences, minimizing waste and environmental impact while maximizing economic efficiency.en-USCC BY-NC-ND 4.0FashionTrend IdentificationMachine LearningMarketing AnalyticsCluster MethodsThesis/Dissertation0009-0009-5900-4069