Abstract
The profit resulting from customer relationship is essential to ensure companies viability, so an improvement in customer retention is crucial for competitiveness. As such, companies have recognized the importance of customer centered strategies and consequently customer relationship management (CRM) is often at the core of their strategic plans. In this context, a priori knowledge about the risk of a given customer to mitigate or even end the relationship with the provider is valuable information that allows companies to take preventive measures to avoid defection. This paper proposes a model to predict partial defection, using two classification techniques: Logistic regression and Multivariate Adaptive Regression Splines (MARS). The main objective is to compare the performance of MARS with Logistic regression in modeling customer attrition. This paper considers the general form of Logistic regression and Logistic regression combined with a wrapper feature selection approach, such as stepwise approach. The empirical results showed that MARS performs better than Logistic regression when variable selection procedures are not used. However, MARS loses its superiority when Logistic regression is conducted with stepwise feature selection.

Abstract
Nowadays, business models play a key role in competitiveness. Each industry has specific needs regarding the customization of their business models. Through a personalized business model, organizations can enjoy a customized mapping of all the business activities. In the machinery industry domain and specifically producers of integrated Products and Services, the need for a customized business model has been growing due to the specifications of the industry. The existing business models do not satisfy the capital goods companies’ needs, therefore a study was conducted to analyze and understand companies’ specifications, the existing supporting business frameworks to further proceed with the creation of a new methodology and framework that supports the businesses of this specific industry.

Abstract
We present a novel mathematical model and a mathematical programming based approach to deliver superior quality solutions for the single machine capacitated lot sizing and scheduling problem with sequence-dependent setup times and costs. The formulation explores the idea of scheduling products based on the selection of known production sequences. The model is the basis of a matheuristic, which embeds pricing principles within construction and improvement MIP-based heuristics. A partial exploration of distinct neighborhood structures avoids local entrapment and is conducted on a rule-based neighbor selection principle. We compare the performance of this approach to other heuristics proposed in the literature. The computational study carried out on different sets of benchmark instances shows the ability of the matheuristic to cope with several model extensions while maintaining a very effective search. Although the techniques described were developed in the context of the problem studied, the method is applicable to other lot sizing problems or even to problems outside this domain.

Abstract
Among the Portuguese artisanal fishing fleets, the bivalve dredge fleet is one of the most profitable. In the last decade, after the implementation of a quotas system, the management of this fishery has been largely focused on adjusting catch to the conservation status of the resources exploited. The present work aims to understand how changes in the amount of quota attributed to each vessel each year and shifts in the quota regime affected vessel productivity. Boostrapped Malmquist indices, complemented with an efficiency assessment using a directional distance function, were used to quantify productivity changes between 1999 and 2011 for the fleets operating in two areas along the Portuguese coast (northwest and southwest). The results showed that the implementation of a weekly quota, as opposed to a daily quota, led to a significant improvement in productivity. This was mainly due to the decrease in fishing days and fuel consumption. It is predicted that the implementation of weekly quotas in the south area would lead to an overall reduction of about 12% in fishing days and fuel consumption, even though the variation in fuel consumption may be affected by the status of the resources. The results achieved provide important insights for future management actions and showed the potential advantages of applying this type of management to other fisheries worldwide, mainly those using active gear.

Abstract
Operations Research/Management Science (OR/MS) can be described as the discipline of applying advanced analytical methods to help making better decisions and has been around in the agricultural and forestry management sectors since the fifties, approaching decision problems that range from more strategic sectorlevel planning to farm operation issues and integrated supply chain management. In this paper insights are given on the use of OR/MS in agriculture, illustrating them with cases drawn from the literature on this topic while keeping the descriptions accessible to uninitiated readers. The presence of OR/MS in Agriculture and Forest Management applications is already extensive but the potential for development is huge in times where resources are becoming increasingly scarce and more has to be done with less, in a sustainable way.

Abstract
In this work we present single-stage formulations for the integrated soft drink lot-sizing and scheduling problem with two-stage synchronization. It is a multi-product, multi-machine problem, with sequence-dependent setup times and costs. Without loss of generality, these single-stage reformulations address the problem correctly and, in general, reduce the size of the synchronized two-stage model of Ferreira, Morabito e Rangel (2009), regarding the number of variables and constraints. The preliminary computational experiments on real-world instances from a soft-drink company show the competitiveness of the single-stage models against other formulations and solution approaches reported in the literature.