Abstract
This paper aims to provide an assessment of urban quality of life (QoL) of European cities from the perspective of qualified human resources. The competitiveness of cities relies increasingly in their capacity to attract highly educated workers, as they are important assets for firms when choosing a location. Qualified human resources, on the other hand, tend to value QoL over other urban features. This is why policymakers and urban planners need to evaluate QoL of cities and be provided with tools that can guide action to improvements in this area. We assess urban QoL by means of a composite indicator constructed using data envelopment analysis, based on Urban Audit data and Mercer's framework of analysis, to give account of 246 European cities. Besides presenting a ranking of the best and the worst scores of QoL, this methodology allows benchmarking strategies.

Abstract
Fierce competition as well as the recent financial crisis in financial and banking industries made credit scoring gain importance. An accurate estimation of credit risk helps organizations to decide whether or not to grant credit to potential customers. Many classification methods have been suggested to handle this problem in the literature. This paper proposes a model for evaluating credit risk based on binary quantile regression, using Bayesian estimation. This paper points out the distinct advantages of the latter approach: that is (i) the method provides accurate predictions of which customers may default in the future, (ii) the approach provides detailed insight into the effects of the explanatory variables on the probability of default, and (iii) the methodology is ideally suited to build a segmentation scheme of the customers in terms of risk of default and the corresponding uncertainty about the prediction. An often studied dataset from a German bank is used to show the applicability of the method proposed. The results demonstrate that the methodology can be an important tool for credit companies that want to take the credit risk of their customer fully into account.

Abstract
The information provided by online traveler reviews is becoming a key element in the decision-making process of hotel customers, reducing the uncertainty and the perceived risk of a traveler. Therefore, a careful analysis of the content provided by online customers' reviews might give invaluable information concerning the key determinants, from a user's perspective, of the quality of the service provided, justifying the attributed service rating. The objectives of this study are twofold: (1) use text-mining techniques to analyze the user's generated content automatically collected from hotels in Porto in a certain period of time and, from this analysis, derive the most frequent terms used to describe the service; (2) understand whether it is possible to predict the aggregated rating assigned by reviewers based on the terms used and, at the same time, identify the terms showing high predictive capacity. Our study attempts to support hotel service managers in achieving their strategic and tactical goals by using innovative text- and data-mining tools to explore the wealth of information provided by user generated content in an easy and timely way.

Abstract
Currently, many libraries, either academic or public, possess information systems to support their operations. Although libraries are becoming more aware of the potential of data analytics in supporting library management decisions, there is still a long way to go to take plenty advantage of the information collected. This paper proposes a prescriptive analytics solution to enhance the service provided by libraries, by optimizing libraries layout. The quantitative method introduced aims to identify layout configurations that minimize the time spent by clients in picking books from the library. A new multi-floor layout optimization algorithm is developed, based on the pairwise exchange method heuristic. A real data sample of approximately 66.000 loans, taken from the information system of a European Engineering School's library, was analyzed and processed. The method proposed was used to improve the library's current departments configuration, achieving an improvement of 13.2% in terms of walking distance to collect the books. The results corroborate the effectiveness of the method proposed and its potential in supporting library management decisions.

Abstract
In the increasingly competitive fashion retail industry, companies are constantly adopting strategies focused on adjusting the products characteristics to closely satisfy customers' requirements and preferences. Although the lifecycles of fashion products are very short, the definition of inventory and purchasing strategies can be supported by the large amounts of historical data which are collected and stored in companies' databases. This study explores the use of a deep learning approach to forecast sales in fashion industry, predicting the sales of new individual products in future seasons. This study aims to support a fashion retail company in its purchasing operations and consequently the dataset under analysis is a real dataset provided by this company. The models were developed considering a wide and diverse set of variables, namely products' physical characteristics and the opinion of domain experts. Furthermore, this study compares the sales predictions obtained with the deep learning approach with those obtained with a set of shallow techniques, i.e. Decision Trees, Random Forest, Support Vector Regression, Artificial Neural Networks and Linear Regression. The model employing deep learning was found to have good performance to predict sales in fashion retail market, however for part of the evaluation metrics considered, it does not perform significantly better than some of the shallow techniques, namely Random Forest.

Abstract
This paper presents a methodology based on random forest algorithm to predict the undergraduate academic performance of students from a polytechnic institution. The approach followed enabled to select 11 explanatory variables, starting from an initial set of around fifty, which allow to obtain a good predictive performance (R-2=0.79). These variables reveal crucial aspects for the definition of management strategies focused on promoting academic success.