Abstract
This paper proposes an ontology-based approach to support the process of visualizing urban mobility data. The approach consists of building a visualization-oriented urban mobility ontology, focused on themes such as ridership, vehicle flows and the like. Existing ontologies focus on modelling the overall structure of transportation networks, and do not address the formalization of such themes. The ontology also allows characterizing visualization techniques with human perception factors, so that they can be used to automatically infer recommended techniques for a dataset. The ultimate goal is to benefit decision makers, by providing an ontology that can assist with the process of developing semantically-rich visualizations, with increased data interoperability and knowledge extraction capabilities. We provide an example with real data of the public transportation system of the city of Porto, Portugal. The example shows the semantic characterization of a visualization technique, and how semantics can assist the task of automatically recommending visualizations. (C) 2017 The Authors. Published by Elsevier B.V.

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 problem of assigning students to teams can be described as maximising their profiles diversity within teams while minimising the differences among teams. This problem is commonly known as the maximally diverse grouping problem and it is usually formulated as maximising the sum of the pairwise distances among students within teams. We propose an alternative algorithm in which the within group heterogeneity is measured by the attributes' variance instead of by the sum of distances between group members. The proposed algorithm is evaluated by means of two real data sets and the results suggest that it induces better solutions according to two independent evaluation criteria, the Davies–Bouldin index and the number of dominated teams. In conclusion, the results show that it is more adequate to use the attributes' variance to measure the heterogeneity of profiles within the teams and the homogeneity among teams. © 2017 SEFI.

Abstract
Customers' response is an important topic in direct marketing. This study proposes a data mining response model supported by random forests to support the definition of target customers for banking campaigns. Class imbalance is a typical problem in telemarketing that can affect the performance of the data mining techniques. This study also contributes to the literature by exploring the use of class imbalance methods in the banking context. The performance of an undersampling method (the EasyEnsemble algorithm) is compared with that of an oversampling method (the Synthetic Minority Oversampling Technique) in order to determine the most appropriate specification. The importance of the attribute features included in the response model is also explored. In particular, discriminative performance was enhanced by the inclusion of demographic information, contact details and socio-economic features. Random forests, supported by an undersampling algorithm, presented very high prediction performance, outperforming the other techniques explored.

Abstract
Understanding the impact of corruption in modern societies, namely in standard of living, health and education services, is an issue that has attracted increased attention in recent years. This paper examines the relationship between the Corruption Perception Index (CPI) provided by Transparency International and the Human Development Index (HDI) of the United Nations Development Program and its components. The analysis is done for clusters of countries with similar levels of development. For the countries with high levels of development, it was found a negative relationship between corruption and human development. Moreover, for these countries, higher corruption levels are related to poor health care services, poor education services and low standard of living. For the other clusters of countries, these relationships were not statistically significant. The results obtained reinforce the importance of efforts by international politicians and organizations in fighting corruption, particularly in highly developed countries, to promote development.

Abstract
This paper develops a decision support tool that can help fishery authorities to forecast bivalve landings for the dredge fleet accounting for several contextual conditions. These include weather conditions, phytotoxins episodes, stock-biomass indicators per species and tourism levels. Vessel characteristics and fishing effort are also taken into account for the estimation of landings. The relationship between these factors and monthly quantities landed per vessel is explored using multiple linear regression models and data mining techniques (random forests, support vector machines and neural networks). The models are specified for different regions in the Portugal mainland (Northwest, Southwest and South) using six years of data 2010-2015). Results showed that the impact of the contextual factors varies between regions and also depends on the vessels target species. The data mining techniques, namely the random forests, proved to be a robust decision support tool in this context, outperforming the predictive performance of the most popular technique used in this context, i.e. linear regression.