Abstract
This paper proposes a new model to predict company failure in the construction industry. The model includes three major innovative aspects. The use of strategic variables reflecting the key specificities of construction companies, which are critical to explain company failure. The use of data mining techniques, i.e. support vector machine to predict company failure. The use of two different sampling methods (random undersampling and random oversampling with replacement) to balance class distributions. The model proposed was empirically tested using all Portuguese contractors that operated in 2009. It is concluded that support vector machine, with random oversampling and including strategic variables, is a very robust tool to predict company failure in the context of the construction industry. In particular, this model outperforms the results obtained with logistic regression.

Abstract
The purpose of this paper is to characterize the competitive positioning of the construction industry companies and evaluate their financial performance. The methodology proposed involves three major stages., The first stage concerns the identification of the competitive positioning of companies within the construction sector. This is achieved using a hierarchical clustering algorithm suitable for large datasets and mixed type variables. The second stage is the analysis of performance of the different clusters. This is done using the Data Envelopment Analysis technique. To characterize in detail the main performance features of each cluster, a decision tree is used to extract the main rules concerning the performance spread within each cluster and the gap between the cluster best practices and the national benchmarks. The third stage concerns the analysis of the strengths, weaknesses and areas of potential improvement for contractors in each competitive positioning. This required the analysis of benchmark companies of each cluster. The methodology proposed was applied for the analysis of performance of all contractors that operate in the Portuguese construction industry.

Abstract
Several fisheries across the world are managed by a quota regime. These quotas can be set yearly, monthly, weekly or daily. However, for some fish species demand seasonality may occur, which should be taken into consideration in the establishment of the quota (especially in those fisheries managed by daily or monthly quotas). This would allow fishermen to catch more fish at times of the year with higher demand in detriment of periods when demand is low. The present work investigates the existence of demand seasonality for bivalves from the artisanal dredge fleet. This fleet operates along the entire coast of the Portugal mainland. The analysis of fleets' revenue efficiency is assessed with Data Envelopment Analysis models, and the monthly seasonality effects on the revenue efficiency were tested using a Tobit regression. The results revealed that on the South coast there is a strong demand in the summer whereas on the western coast (northwest and southwest fishing areas) demand increases during Christmas and New Year festivities. Since this fishery is managed by weekly/daily quotas, it is proposed that these quotas should be redistributed in order to adjust them to periods of higher demand, thereby increasing the profitability of the vessels. The approach followed could be applied to similar fisheries worldwide.

Abstract
Assessing eco-efficiency of companies is important to ensure the creation of wealth without compromising the needs of future generations. This work aims to extend the eco-efficiency concept by including in the assessment new features related to environmental benefits and environmental burdens. This concept is implemented using an innovative Directional Distance Function model, which searches for improvements in the magnitude of the indicators and in the composition of the resources consumed. This framework can help firms to become more sustainable by replacing non-renewable inputs with "greener" alternatives. We present an empirical application to large mining companies. Different scenarios regarding managerial priorities for adjustments to firms' economic and environmental indicators are explored. The results obtained and their managerial implications are discussed in the context of mining firms activity.

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.