Abstract
With the aim of disseminating the potential and the capacity of Educational Data Mining (EDM) as an instrument of investigation and analysis in the support to the management of Higher Education Institutions, this paper presents a brief description of some of the most relevant studies in the area. The analysis carried out allows to highlight the innovations that EDM has been promoting, as well as current and future research trends.

Abstract
The early classification of university students according to their potential academic performance can be a useful strategy to mitigate failure, to promote the achievement of better results and to better manage resources in higher education institutions. This paper proposes a two-stage model, supported by data mining techniques, that uses the information available at the end of the first year of students' academic career (path) to predict their overall academic performance. Unlike most literature on educational data mining, academic success is inferred from both the average grade achieved and the time taken to conclude the degree. Furthermore, this study proposes to segment students based on the dichotomy between the evidence of failure or high performance at the beginning of the degree program, and the students' performance levels predicted by the model. A data set of 2459 students, spanning the years from 2003 to 2015, from a European Engineering School of a public research University, is used to validate the proposed methodology. The empirical results demonstrate the ability of the proposed model to predict the students' performance level with an accuracy above 95%, in an early stage of the students' academic path. It is found that random forests are superior to the other classification techniques that were considered (decision trees, support vector machines, naive Bayes, bagged trees and boosted trees). Together with the prediction model, the suggested segmentation framework represents a useful tool to delineate the optimum strategies to apply, in order to promote higher performance levels and mitigate academic failure, overall increasing the quality of the academic experience provided by a higher education institution.

Abstract
This chapter discusses the development of improved citizen services taking into consideration integration of agent-based modelling and simulation experience into conceiving, design and implementation activities with a strong focus on technology enabled service systems. Service design is formalized here towards the integration of customer experience, validated through service interaction modelling. Integration of user experience at design stage in the value co-creation process is a possible immediate evolution direction of projects in the Smarter Cities perspective. Guidelines for integrating a modelling and simulation perspective in service design are presented along with the Socio-Technical Systems Engineering process. The case study presented here is dedicated to Smart Transport. The chapter opens a larger discussion on specific research directions and knowledge transfer related to Smart Transport as highlighted in EU projects.

Abstract
This paper describes an exploration process aligned with the core domain of Service Science inside a critical sector of Society, aiming at developing City in a sustainable, responsible, inclusive way. The paper focuses on defining the Public Safety as a Service concept in an inclusive and responsible value co-creation urban design vision for liveable cities. It explains how service intelligence can act on immaterial artefacts to transform data into information to generate value co-creation processes whose outcomes are applied to the evolution of knowledge in public safety services. Public safety is approached within a service ecosystem perspective, following the global targets of the Sendai Framework for Disaster Risk Reduction as an application perspective. Managerial implication are approached from two perspectives: establishment of governance principles with the help of Elinor Ostrom's works, and a Viable Systems Approach on the response to disasters operating rules.

Abstract
This paper investigates the performance of the largest Brazilian hydropower plants. This study covers 78% of the total installed capacity from hydros in the country, and considers indicators reflecting operational and maintenance costs as well as quality of service. The assessment was conducted using a new approach for the construction of composite indicators, based on a directional distance function model. First, we assessed the hydropower plants allowing for complete flexibility in the definition of weights, enabling the identification of underperforming plants, and quantification of their potential for improvement. Next, we assessed the plants considering different perspectives regarding the importance attributed to each indicator. This allowed reflecting different points of view, focusing primarily on operation and maintenance costs or quality issues. The results identify the hydropower plants that can be considered benchmarks in different scenarios, and allow testing the robustness of plants' classification as benchmarks in the unrestricted model.

Abstract
The personal characteristics of entrepreneurs can be importantly related to entrepreneurial startup intentions and behaviors. A country-moderated hypothesis including the relationship between an individual's risk-taking propensity and entrepreneurship (behaviors or intentions of the person) was conceptually developed and empirically tested in this study. The data collection was performed through a structured questionnaire. Multinominal logistic regression was used for analyzing data obtained from 1,414 students in six countries. The crucial contribution of this research is the clarification of the character of risk-taking propensity in entrepreneurship and the indication that the risk-taking propensity-entrepreneurship relationship can be moderated contingent on power distance.