Demand estimation with text and image data
File(s)
Published version (early view)
Author(s)
Compiani, Giovanni
Morozov, Ilya
Seiler, Stephan
Type
Journal Article
Abstract
We propose a demand estimation approach that leverages unstructured data to infer substitution patterns. Using pre-trained deep learning models, we extract embeddings from product images and textual descriptions and incorporate them into a mixed logit demand model. This approach enables demand estimation even when researchers lack data on product attributes or when consumers value hard-to-quantify attributes such as visual design. Using a choice experiment, we show this approach substantially outperforms standard attribute-based models at counterfactual predictions of second choices. We also apply it to 40 product categories offered on Amazon.com and consistently find that unstructured data are informative about substitution patterns.
Date Issued
2026-03-23
Date Acceptance
2026-03-03
Citation
The RAND Journal of Economics, 2026
ISSN
0741-6261
Publisher
Wiley
Journal / Book Title
The RAND Journal of Economics
Copyright Statement
© 2026 The Author(s). The RAND Journal of Economics published by Wiley Periodicals LLC on behalf of The RAND Corporation. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
License URL
Publication Status
Published online
Date Publish Online
2026-03-23