A Deep Learning Approach to Heterogeneous Consumer Aesthetics in Fast Fashion

TL;DR

This paper develops a deep learning framework using Fashion CLIP embeddings and demand modeling to analyze consumer preferences and pricing in fast fashion, capturing heterogeneity and demand responses.

Contribution

It introduces a scalable, multimodal embedding-based demand system that captures consumer heterogeneity and informs pricing and sustainability analysis in fashion.

Findings

Deep demand system outperforms alternatives in capturing substitution patterns.

Machine learning hedonic models improve quality-adjusted price indices.

Demand responses vary significantly across product and user clusters during COVID-19.

Abstract

Aesthetics drives product differentiation in industries such as fashion, interior decor, luxury goods, real estate and hospitality. However, visual differentiation is hard to encode in formal economic analysis. This paper analyses millions of purchase records from H\&M in the Netherlands, including product images, text descriptions, prices, and consumer demographics. I fine-tune Fashion CLIP embeddings with a three-tower approach that builds separate channels for product visuals and text, consumer history, and price, which makes downstream analysis tractable and scalable. The embeddings feed a latent-class deep demand system that captures price and taste sensitivities through deep nets, recovers rich substitution patterns, reveals meaningful heterogeneity, and performs much better than competing alternatives. Then, a supply-side inversion recovers sensible markups and costs and supports conduct tests and counterfactuals on sustainability practices. I also estimate machine learning hedonic pricing models that perform much better than competing alternatives. This model allows us to construct quality-adjusted price indices, make it possible to price completely new designs, and with an Oaxaca-Blinder decomposition reveal the underlying sources of price changes. Finally, a Poisson event study around the COVID-19 lockdown shows that the range of demand responses across embedding-based product and user clusters exceeds anything recoverable from simple text-based attributes or demographic labels alone. The methodology is portable to any market where products are differentiated along sensory dimensions that are hard to encode but meaningfully important for consumer choices.