Learning user preferences of route choice behaviour for adaptive route guidance

Current navigation systems help drivers in the task of driving and hence improve safety. However, they could be even more useful if route guidance were personalised by incorporating user preferences, which would also improve user satisfaction. This paper presents a route selection model developed for personalised route guidance. The model adaptively changes route selection rules when it discovers the predicted choice differs from the actual choice of the driver. In this study, the route selection rules are generated by using a decision tree learning algorithm, the C4.5 algorithm, which has advantages over other data mining methods in terms of its comprehensible model structure. A simulation experiment was conducted to analyse the applicability of the learning model to adaptive route guidance and the accuracy of its prediction with a real-world network.