Demand Estimation with Text and Image Data
This addresses the problem of demand estimation for researchers and businesses when product attributes are missing or hard to quantify, though it is incremental as it builds on existing models with new data types.
The paper tackles demand estimation by using text and image data to infer substitution patterns, showing that this approach outperforms standard attribute-based models in counterfactual predictions and consistently identifies close substitutes across 40 Amazon product categories.
We propose a demand estimation method that leverages unstructured text and image 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 random coefficients logit model. This approach enables researchers to estimate demand even when they lack data on product attributes or when consumers value hard-to-quantify attributes, such as visual design or functional benefits. Using data from a choice experiment, we show that our approach outperforms standard attribute-based models in counterfactual predictions of consumers' second choices. We also apply it across 40 product categories on Amazon and consistently find that text and image data help identify close substitutes within each category.