Econometrics with Pre-Trained Embeddings for Unstructured Data
Read the original on arXiv Statistics ML →The paper examines the use of pre‑trained deep‑learning embeddings as covariates in economic analyses of unstructured data. It identifies two main challenges: the mismatch between training data/tasks of pre‑trained models and the target economic task, and the identification problem of the embedding function. The authors propose sufficient conditions—particularly a transferability criterion—to guarantee convergence, introduce a bootstrap test to assess transferability without re‑estimating embeddings, and apply the framework to various double‑machine‑learning settings, including an empirical study of labor‑supply elasticity on Amazon Mechanical Turk using job‑description embeddings.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.