Financial institutions are faced with the need to assess the creditworthiness of a borrower that applies for a loan. In this regard, data scientistscan produce valuable insights that can explain customer profile and behavior. This paper proposes an analysis of a database of customers where a part of them were unable to repay their loans and got into default status. By using the methodology of data mining and machine learning algorithms, a series of predictive models were developedusing classifiers such as LightGBM, XGBoost, Logistic Regression and Random Forest in order to evaluate the probability of a customer's enteringloan default. Three sampling scenarios were created to compare the classification between imbalanced and balanced data sets. Moreover, a model comparison analysis was performed to identify the best classifier by considering the model performance metrics: AUC score, Precision, Recall and Accuracy. The best results were observed for the Random Forest optimal classifier applied on the combined scenario under-over sampling, with a representative AUC of 0.89.

Tobacco consumption is a problem of both health and economic interest nowadays. According to recent studies conducted by the European Commission approximate 700,000 deaths per year are caused by smoking. For this reason, the European Commission frequently conducts a survey in order to monitor the attitude towards tobacco addiction. Smoking addiction changes due to different factors such as budget, time or entourage. The evolution in time of these factors and the consumers’ preferences is studied using behavioral economics based on a small group of respondents. Through a survey, over 500 persons were asked to choose their preference for cigarettes characteristics. We employ correspondence analysis using combinations of age, type of cigarette, number of cigarettes smoked per day and nicotine concertation to see the type of responses the consumers’ have according to their habit. Moreover, we made a 5 persons selection from the initial group and we observed their behavior for 9 months period of time. The consumers were asked to classify a set of packages according to their preferences and we applied conjoint analysis in order to determine how or if the initial preferences change. Furthermore, we explain the changes in behavior by taking into account the nowadays global impetus towards a healthier lifestyle. The results provided allow to emphasize the role of a strong analysis for each single target consumer’s behavior as this is one of the main roles of Behavioral Economics.

Higher Education Institutions often struggle to optimally use their available resources in pursuance of both educational and research outputs, while competing for gathering funds. Furthermore, increasing teaching burden for academic workforce may shrink their time dedicated to research, which may also negatively impact the budget. The aim of this paper consists in examining the efficiency of two important dimensions of European universities (teaching and research), together with a possible ranking based on the models we employ for each of these two perspectives. Our target is to also explore any possible compromises between education and scientific research. We employ non-parametric efficiency analysis using FDH (Free Disposal Hull) and Hyperbolic efficiency estimators for a sample of 264 universities for the year 2014, from the RISIS-ETER facility, a database of European Higher Education Institutions and their indicators. Filters are applied to the initial heterogenous dataset in order to obtain adequate efficiency models that analyse universities performance from both research and teaching perspectives. Teaching efficiency is defined by how well the institutions manage to use their government allocation and academic staff in producing the maximum amount of undergraduate degrees, whereas the research efficiency is given by how well the universities perform in maximizing their research outputs considering only the personnel involved in research activities. The results illustrate that many institutions are focusing into a single direction and some efforts need to be undertaken in order to improve the academic