A Neural-embedded Choice Model: TasteNet-MNL Modeling Taste Heterogeneity with Flexibility and Interpretability
Published in
arXiv.org(2020)External Links:
TL
TL;DR
TasteNet-MNL can recover the underlying non-linear utility function, and provide predictions and interpretations as accurate as the true model; while examples of logit or random coefficient logit models with misspecified utility functions result in large parameter bias and low predictability.