| dc.description.abstract | The rapid evolution of the global fashion retail industry has created increasing demand
for intelligent, data-driven solutions that enhance personalization, increase predictive
accuracy, and facilitate sustainable shopping experiences. In a time of rapidly shifting
consumer preferences and the growth of digital commerce, traditional retail strategies
that rely on manual trend prediction, static customer profiling, and fragmented decision making processes are no longer adequate. This review aims to examine and critically
analyse modern artificial intelligence (AI) tools utilized in fashion retail, such as
computer vision for product recognition, AI-powered trend forecasting, personalized
recommendation systems, and sustainability-focused decision support systems. Major
academic databases were used to conduct a systematic literature review of peer-reviewed
studies published between 2018 and 2025, guaranteeing thorough coverage of the
technological developments influencing contemporary retail practices. Based on the
analysis and synthesis of findings reported in the reviewed studies, AI-driven innovations
are shown to improve customer engagement, support inventory planning, reduce
overproduction, and enhance the ability to predict market shifts, although the reported
outcomes vary across application areas and study designs. Additionally, several studies
indicate that integrated AI systems enable enhanced user interaction across omni channel platforms by supporting more personalized shopping experiences. Despite
these developments, issues related to methodological consistency, real-world deployment,
and dataset diversity are repeatedly identified in the reviewed literature, highlighting the
need for further research and refinement. This review consolidates existing evidence,
identifies key research gaps, and proposes a conceptual framework to support future
AI-enabled fashion retail solutions. | en_US |
