Demand Estimation with Text and Image Data

Arbeitspapier

We propose a demand estimation method that allows researchers to estimate substitution patterns from unstructured image and text data. We first employ a series of machine learning models to measure product similarity from products' images and textual descriptions. We then estimate a nested logit model with product-pair specific nesting parameters that depend on the image and text similarities between products. Our framework does not require collecting product attributes for each category and can capture product similarity along dimensions that are hard to account for with observed attributes. We apply our method to a dataset describing the behavior of Amazon shoppers across several categories and show that incorporating texts and images in demand estimation helps us recover a flexible cross-price elasticity matrix.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: CESifo Working Paper ; No. 10695

Classification and Topics

• Classification: Wirtschaft ; Econometric and Statistical Methods and Methodology: General ; Econometric Modeling: General ; Methodology for Collecting, Estimating, and Organizing Microeconomic Data; Data Access
• Subject: demand estimation ; unstructured data ; computer vision ; text models

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Compiani, Giovanni ; Morozov, Ilya ; Seiler, Stephan
• Event: Veröffentlichung
• (who): Center for Economic Studies and ifo Institute (CESifo)
• (where): Munich
• (when): 2023

Further information

• Handle: http://hdl.handle.net/10419/282383
• Last update: 10.03.2025, 11:44 AM CET