Causal Inference in Sustainable Fashion Concern: Anomaly Detection and Explanation Discovery with Big Data
Abstract
The fashion industry is increasingly transitioning towards sustainability, driven by changing consumer preferences and a global ethical imperative. Big data analytics revolutionizes how trends are analyzed, consumer behavior is understood, and innovation is fostered in the textile and apparel sector. However, there are significant challenges in comprehending the dynamics of consumer engagement and public interest shifts, particularly in response to external stimuli such as disasters, social movements, and political events. This study addresses these challenges by applying complex systems theory to investigate the influence of these external factors on consumer attitudes and behaviors. Using anomaly detection and explanation discovery techniques, the research reveals how these factors, coupled with the evolving digital landscape, shape consumer engagement in the context of sustainable fashion. The findings offer crucial insights for industry practitioners and policymakers, contributing to a better understanding of the external forces that drive the shift toward sustainability in fashion.
Keywords: Sustainable Fashion, Consumer Concern, Big Data Analytics, Complex Systems Theory, Anomaly Detection, Industry Practitioners
How to Cite:
Zeng, L. & Lin, X., (2025) “Causal Inference in Sustainable Fashion Concern: Anomaly Detection and Explanation Discovery with Big Data”, International Textile and Apparel Association Annual Conference Proceedings 81(1). doi: https://doi.org/10.31274/itaa.18789
Downloads:
Download PDF
View PDF
51 Views
15 Downloads