Enhancing choice-set generation and route choice modeling with data- and knowledge-driven approach

Two central and interconnected problems arise in the specification of a "complete" path-based route choice model: choice-set generation and choice from a choice set. Choice-set generation poses a significant challenge in personalization and the enumeration of the full choice set with large size. Despite the continued prevalence of classic econometric models for modeling choices within a given set, this requirement of knowledge-driven modeling necessitates explicit model structures and intricate domain knowledge, which may result in practical biases. In this study, a Conditional Variational AutoEncoder (CVAE)-based choice set generation model is developed, which approximates the probability distribution of the underlying choice set generation process conditional on individual and OD characteristics without relying on expert knowledge. In order to facilitate a friendly integration between knowledge-driven econometric and machine learning approaches, a neural-embedded route choice model (IAP-NERCM) with implicit availability/ perception (IAP) of choice alternatives is proposed to automatically capture the heterogeneity of taste parameters without assuming any a priori relationship. Results based on synthetic data show that the proposed models are capable of reproducing the pre-defined coefficients. Field data of GPS data collected in Toyota City is used to future test the proposed models compared to classical statistical models. Results indicate that IAP-NERCM exhibits the ability to recover underlying taste function and achieves the best performance in terms of goodness-of-fit, predictability, and estimation time.