A model of drivers' route choice behavior under advanced traveler information systems (ATIS) is developed based on data collected from learning experiments using interactive computer simulation. A neural network model is used as a convenient modeling technique in the analysis. Results indicated that most subjects made route choices based mainly on their recent experiences. Results also demonstrated that route choice behavior is related to the personal characteristics as well as the characteristics of the respective routes. Travel experiences had less effect on route choice and the results indicate that the prediction accuracy of the model, the acceptance rate of advice, and the quality of advice are closely related.