Mining Temporal Patterns of Transport Behaviour for Predicting Future Transport Usage

Authors

Abstract

There is huge potential in increasing the value of public transportation by creating novel travel information systems which are centred on the individual transport user. Especially, in dense urban cities where it is hard to oversee complex transport networks that are subject to frequent changes, maintenance and construction works, travellers want to be proactively notied about disruptions and trac incidents relevant to their future behaviour. In this paper, we show how to mine characteristic patterns about the transport routines of urban bus riders for the design of novel travel information system that have the ability to understand forthcoming travel needs of individual users. We leverage on travel histories collected from automated fare collection system (AFC) to extract features of personal transport usage and predict whether people access public transport services on a future day or not. In order to design an accurate predictor, we study the predictive power of four temporal features of transport behaviour and devise an eective prediction approach which is able to forecast future transport usage with an average prediction accuracy of 77%

Conference

Third International Workshop on Pervasive Urban Applications (PURBA) in conjunction with ACM International Joint Conference on Pervasive and Ubiquitous Computing, September 2013