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
Purpose - The purpose of this paper is to understand value cocreation in service ecosystems from a multilevel perspective, uncovering value cocreation factors and outcomes at the micro, meso, and macro levels. Design/methodology/approach - A Grounded Theory approach based on semi-structured interviews is adopted. The sample design was defined to enable the ecosystem analysis at its different levels. At the macro level was the Portuguese Health Information ecosystem. Embedded meso level units of analysis comprised eight health care organizations. A total of 48 interviews with citizens and health care practitioners were conducted at the micro level. Findings - Study results enable a detailed understanding of the nature and dynamics of value cocreation in service ecosystems from a multilevel perspective. First, value cocreation factors are identified (resource access, resource sharing, resource recombination, resource monitoring, and governance/institutions generation). These factors enable actors to integrate resources in multiple dynamic interactions to cocreate value outcomes, which involve both population well-being and ecosystem viability. Study results show that these value cocreation factors and outcomes differ across levels, but they are also embedded and interdependent. Practical implications - The findings have important implications for organizations that are ecosystem actors (like the Portuguese Ministry of Health) for understanding synergies among value cocreation factors and outcomes at the different levels. This provides orientations to better integrate different actor roles, technology, and information while facilitating ecosystem coordination and co-evolution. Originality/value - This study responds to the need for a multilevel understanding of value cocreation in service ecosystems. It also illuminates how keystone players in the ecosystem should manage their value propositions to promote resource integration for each actor, fostering resource density and ecosystem viability. It also bridges the high-level conceptual perspective of Service-Dominant logic with specific empirical findings in the very important context of health care.

Abstract
Service innovation is often viewed as a process of accessing the necessary resources, (re)combining them, and converting them into new services. The current knowledge on success factors for service innovation, such as formalized new service development (NSD) processes, predominantly comes from studying large firms with a relatively stable resource base. However, this neglect situations in which organizations face severe resource constraints. This paper argues that under such constraints, a formalized new service development process could be counter-productive and a bricolage perspective might better explain service innovation in resource constrained environments. In this conceptual paper, we propose that four critical bricolage capabilities (addressing resource scarcity actively, making do with what is available, improvising when recombining resources, and networking with external partners) influence service innovation outcomes. Empirical illustrations from five organizations substantiate our conceptual development. Our discussion leads to a framework and four testable propositions that can guide further service research.

Abstract

Abstract

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.