Simultaneous Modeling of Mobility Tool Ownership in Agent-Based Travel Demand Models: A Comparison of Discrete Choice and Machine Learning Models

Individual travel behavior, such as mode choice, is determined to a distinct degree by the respective portfolio of available mobility tools, such as the number of cars, public transit pass ownership, or a carsharing membership. However, the choice of different mobility tools is interdependent, and individuals weigh alternatives against each other. This process of parallel trade-offs is currently not reflected in typically used sequential logit models of agent-based travel demand models. This paper fills this research gap by applying discrete choice and neural network models on a synthetic population to model multiple mobility tool ownership simultaneously. Using data from a national household travel survey, both model types approximate given target distributions of mobility tools more accurately than the sequence of three corresponding logit models. Due to the higher flexibility, the tested shallow and deep neural network exhibit higher predictive accuracy than simultaneous discrete choice models. The results indicate that neural networks with only one hidden layer are more robust and easier to formulate and interpret than deep networks with three hidden layers. ... mehrThe universal applicability of the flat neural network is observed by transferring the model to a different synthetic population resulting in equally accurate results.