2 code implementations • 3 Feb 2020 • Yafei Han, Francisco Camara Pereira, Moshe Ben-Akiva, Christopher Zegras
Our formulation consists of two modules: a neural network (TasteNet) that learns taste parameters (e. g., time coefficient) as flexible functions of individual characteristics; and a multinomial logit (MNL) model with utility functions defined with expert knowledge.