Abstract
The public transport system integrates a complex ecosystem, composed not only by transport operators and travellers but also by other services such as schools, firms, restaurants, museums, banks, and public establishments. Therefore, by adopting a holistic point of view, we propose a new service approach linking city services and public transport. This approach consists in partnerships that may include discounts, combined packages, reduced prices, deals and marketing campaigns, targeted to each specific audience. In order to develop these partnerships it is important to analyse the services located around the stations and the public transport usage. We use the city of Porto, Portugal, as an illustrative example and we rely on two data sources: Automated Fare Collection system data and business data points. The analysis of both datasets allowed us to determine the level of concentration of city services located around public transport stations and to identify the types of services that tend to agglomerate near the stations. We were also able to analyse the correlation between the number of travel card validations and the number of services located around the stations. Finally we present a case of a service exposure to different demographic segments.

Abstract
The adoption of smart cards in urban public transport has fundamentally changed how transport providers manage and plan their networks. Traveller information services, in particular, have leveraged this contextual data for targeting passengers and providing relevant information. Thus, it becomes increasingly relevant for the next generation of services to obtain on-time contextual passenger information, to support the development of intelligent information services. In this paper an adaptation of the Top-K algorithm is proposed for predicting journey destination, applied to different scenarios in public transport. The performance and efficiency are analysed and compared to a decision tree classifier. Finally, the feasibility and potential of applying the proposed methods to large-scale systems in a real-world environment is discussed.

Abstract
In public transport, smart card-based ticketing system allows to redesign the UPT network, by providing customized transport services, or incentivize travelers to change specific patterns. However, in open systems, to develop personalized connections the journey destination must be known before the end of the travel. Thus, to obtain that knowledge, in this study three models (Top-K, NB, and J48) were applied using different groups of travelers of an urban public transport network located in a medium-sized European metropolitan area (Porto, Portugal). Typical travelers were selected from the segmentation of transportation card signatures, and groups were defined based on the traveler age or economic conditions. The results show that is possible to predict the journey’s destination based on the past with an accuracy rate that varies, on average, from 20% in the worst scenarios to 65% in the best. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
In public transport, traveler dissatisfaction is widespread, due to long waits and travel time, or the low frequency of the service provided. Public transport providers are increasingly concerned about improving the service provided. To improve public transport, detailed knowledge of the network and its weaknesses is necessary. An easy and cheap way to achieve this information is to extract knowledge from the data daily collected in a public transport network. Thus, this chapter focuses on data analysis resulting from the smartcard-based ticketing system. The main objective is to detect patterns of average speed for all days of the week and times of the day, along with pairs of consecutive stops. To perform the analyses, the average speed was deduced from ticketing data, and clustering methods were applied. The results show that it is possible to find segments with similar patterns and identify days and times with similar patterns.