Forecasting the Travel Behavior with Autonomous Vehicles and Car-Sharing—A Case Study of South Korea

For industries closely affected by consumer needs, it is difficult to predict how new technology will diffuse depending on the socio-cultural environment and users’ characteristics. Therefore, the model was developed to forecast how new technologies, such as autonomous vehicles or car-sharing services, would impact individual travel. This model built the travel mode selection algorithm based on the vehicle choice algorithm to forecast the change in consumer transport usage by autonomous vehicles and car-sharing, including consumer preferences for vehicle attributes and consumers’ expectations of new technologies. Furthermore, the algorithm based on the multinomial logit model and agent-based model can calculate the probability of choosing individual travel, considering one’s characteristics. In this model, consumers are individual actors who differentiate between socio-demographic characteristics such as gender, age, number of household members, number of children, and occupational status. Thus, it is a simple agent-based model where each agent’s different behavior creates new phenomena.