Paper Title
Beyond Retail: Predicting High-Demand Sneaker Prices With Machine Learning

Abstract
The sneaker resale market has rapidly emerged as a dynamic intersection of cultural trends and financial opportunities. With limited-edition releases, celebrity collaborations, and global accessibility through platforms like StockX, sneakers have become a unique alternative investment class. This study investigates the sneaker resale industry, highlighting both its significant profit potential—where some sneakers resell at over 200% of their retail value— and its inherent challenges, including price volatility and storage risks. Leveraging machine learning, we construct a predictive pricing model based on StockX data to analyze factors influencing resale prices. Our methodology integrates data preprocessing, exploratory analysis, and predictive modeling, achieving an R² score of 0.837. Key findings emphasize the influence of variables such as retail price, region, and brand on resale values. This research bridges cultural phenomena and data-driven strategies, offering actionable insights for investors and evaluating the viability of sneakers as a profitable investment vehicle in an evolving and volatile market landscape. Keywords - Sneaker Resale Market, Machine Learning, StockX, Alternative Investments