A variational autoencoder approach for choice set generation and implicit perception of alternatives in choice modeling

Abstract

Choice set generation is a challenging task, since the consideration set is generally unknown to the modelers, and the full choice set could be too large to be enumerated. The proposed variational autoencoder approach (VAE) is motivated by the idea that the chosen alternatives must belong to the consideration set. The proposed VAE method explicitly considers maximizing the likelihood of including the chosen alternatives in the choice set and inferring the underlying generation process. This paper derives the generalized extreme value (GEV) model with implicit availability/perception (IAP) of alternatives, for bridging the VAE with choice modeling. Specifically, the cross-nested logit (CNL) model with IAP is derived as an example of IAP-GEV models. The IAP approach assumes each alternative is associated with an implicit degree of availability/perception (likelihood in the context of VAE) to be included in the choice set. The VAE approach for route choice set generation is illustrated in a toy network. Simulation experiments show that the proposed method could reproduce the pre-defined true values. We further exemplify the VAE approach using a real dataset. The IAP-CNL model estimated has the best performance in terms of goodness-of-fit and prediction performance, compared to multinomial logit models and conventional choice set generation methods.