From Unstructured Data to Demand Counterfactuals: Theory and Practice
By: Timothy Christensen, Giovanni Compiani
Potential Business Impact:
Fixes computer predictions about what people buy.
Empirical models of demand for differentiated products rely on low-dimensional product representations to capture substitution patterns. These representations are increasingly proxied by applying ML methods to high-dimensional, unstructured data, including product descriptions and images. When proxies fail to capture the true dimensions of differentiation that drive substitution, standard workflows will deliver biased counterfactuals and invalid inference. We develop a practical toolkit that corrects this bias and ensures valid inference for a broad class of counterfactuals. Our approach applies to market-level and/or individual data, requires minimal additional computation, is efficient, delivers simple formulas for standard errors, and accommodates data-dependent proxies, including embeddings from fine-tuned ML models. It can also be used with standard quantitative attributes when mismeasurement is a concern. In addition, we propose diagnostics to assess the adequacy of the proxy construction and dimension. The approach yields meaningful improvements in predicting counterfactual substitution in both simulations and an empirical application.
Similar Papers
Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes
Machine Learning (CS)
Makes AI learn better with less data.
Identifying counterfactual probabilities using bivariate distributions and uplift modeling
Machine Learning (CS)
Finds out if a sale *really* made a customer buy.
Graph Diffusion Counterfactual Explanation
Machine Learning (CS)
Helps AI explain why it makes graph decisions.