Transit Trip Planners: Real-Time Strategy-Based Path Recommendation

Abstract

In order to improve the effectiveness of information provided to travelers of a transit network, the new generation of trip planners should give recommendations taking into account several factors, such as network unreliability and presence of diversion nodes where path decision can be made according to the occurrences of random events. In this context, travelers have not to rely on a single selected path, but they have to use a strategy, i.e. set of rules that allow travelers to reach the destination maximizing their expected utility. The availability of real-time predictive information requires the traditional optimal hyper-path approaches to be overcame and new ones to be developed. Further, as the values of path attributes forecasted are random variables and therefore, also with an information system, the uncertainty is not completely overcome. This paper explores some aspects of providing path recommendations in unreliable network, proposing a methodology for defining real-time optimal strategies, that combine predictive and expected values of path attributes.