AI-DRIVEN FASHION COMMERCE: REAL-TIME BIDDING FOR PERSONALIZED APPAREL EXPERIENCES

Abstract

The rapid evolution of digital commerce has intensified the need for personalized and adaptive shopping experiences, particularly in the fashion industry where consumer preferences are highly dynamic. This study investigates the integration of artificial intelligence (AI) and real-time bidding (RTB) as a dual framework for delivering personalized apparel recommendations. A simulated e-commerce platform involving 2,500 participants was developed to compare three conditions: traditional recommendation systems, AI-based personalization without RTB, and AI-driven personalization with RTB. Results indicate that AI personalization significantly improved consumer engagement, satisfaction, and conversion rates compared to the control group, while the addition of RTB further amplified these outcomes by increasing contextual relevance, reducing bounce rates, and enhancing session completion. Regression and structural equation modeling analyses confirmed that trust in recommendations and user engagement mediated the relationship between personalization and purchase intent. The findings highlight the commercial potential of AI + RTB integration in fashion commerce, while also emphasizing the need to address ethical considerations surrounding data privacy and algorithmic transparency. This research contributes to both theory and practice by demonstrating how AI-driven personalization, reinforced through RTB, can create meaningful, consumer-centric apparel shopping experiences.