Adventures in Demand Analysis Using AI

Dr. Chernozhukov will present advances in empirical demand analysis achieved by integrating multimodal product representations derived from artificial intelligence (AI). Using a detailed dataset of toy cars on Amazon.com, the research combines text descriptions, images, and tabular covariates to represent each product using transformer-based embedding models. These embeddings capture nuanced attributes, such as quality, branding, and visual characteristics, that traditional methods often struggle to summarize. The findings illustrate that AI-driven representations can enrich and modernize empirical demand analysis. The paper was written with Philipp Bach, Sven Klaassen, Martin Spindler, Jan Teichert-Kluge, and Suhas Vijaykumar.