Search

Having the ability to predict the price of a particular stock share is undoubtedly a major challenge, because of the complexity and implied volatility of the financial markets. This is a topic of great interest to researchers and market players, as the effectiveness of the forecast might translate into huge monetary gains. This work aims to demonstrate the use of neural networks for stock price forecasting. Two financial titles are considered: Microsoft and Apple. The initial choice of the predictor variables comprises the most used and referenced in the scientific papers published on this subject. This work demonstrates the importance of a careful selection of some of those variables for a good neural network performance. published

Wine companies are usually operating in larger and diverse markets and consumers show different needs. Given resource constraints, companies must segment the market, because they cannot cover the entire market or, if they do, they need to adopt and implement an appropriate marketing strategy. Market segmentation enables to treat consumers differently through a marketing strategy geared to this purpose. There are several segmentation criteria and one of them is the wine consumption occasion. Here, like other authors do, we consider the following five situations where the consumer pays for a bottle of wine: to drink at home, to drink at home with friends, to drink at a restaurant, to give as a gift and in businesses. We asked to 133 consumers, randomly selected, how much they were willing to pay in each situation: < 1 Euro; 1 – 2 Euros; 2 – 5 Euros; 5 – 10 Euros; 10 – 20 Euros; > 20 Euros. We concluded that the price decision depends on the wine consumption occasion (Friedman test, p-value=0,000). This is in accordance with the literature. Furthermore, we found something that, to our knowledge, is new: at a 5% level of significance, there is no difference between the situations “to drink at home” and “to drink at home with friends” and also between “to drink at a restaurant”, “to give as a gift” and “in businesses”; the difference lies between the former two situations and the latter three. This means that, for market segmentation, we can consider two instead of five wine consumption occasions. We further investigate how this conclusion depends on consumer gender. published

O Aeroporto Francisco Sá Carneiro e o turismo na região Norte de Portugal têm crescido de forma muito significativa nos últimos anos. Este artigo apresenta um estudo da relação entre o número de passageiros que circulam no aeroporto e as dormidas na região. O estudo é baseado numa análise de regressão linear simples. Como resultado, propõe-se uma forma de prever as dormidas, conhecido o número de passageiros. published

A previsão do número de dormidas mensais é um problema importante para a gestão dos alojamentos turísticos. Neste trabalho, analisa-se a série temporal do número de dormidas mensais na região Norte de Portugal entre janeiro de 2009 e junho de 2017, e obtêm-se previsões através da aplicação de redes neuronais e da análise espectral singular. published

Managing an airport is very complex. Decisions are often based on common sense and influence several variables, such as flight delay. In a previous work, we conducted a preliminary study where we were interested in predicting flight departure delay at Porto Airport. The problem was treated as an ordinal classification task and we built classifiers based on the unimodal paradigm. Here, we consider other approaches to ordinal classification and compare the performance of the resulting classifiers. published

A partir de la crisis financiera del año 2002 se procesaron una serie de transformaciones en la industria bancaria uruguaya. En primer lugar desaparecen las instituciones bancarias declaradas en bancarrota. En segundo lugar se asiste a una recomposición d