Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Short-term electricity load forecasting with machine learningPublication . Aguilar Madrid, Ernesto; António, NunoAn accurate short-term load forecasting (STLF) is one of the most critical inputs for power plant units’ planning commitment. STLF reduces the overall planning uncertainty added by the intermittent production of renewable sources; thus, it helps to minimize the hydrothermal electricity production costs in a power grid. Although there is some research in the field and even several research applications, there is a continual need to improve forecasts. This research proposes a set of machine learning (ML) models to improve the accuracy of 168 h forecasts. The developed models employ features from multiple sources, such as historical load, weather, and holidays. Of the five ML models developed and tested in various load profile contexts, the Extreme Gradient Boosting Regressor (XGBoost) algorithm showed the best results, surpassing previous historical weekly predictions based on neural networks. Additionally, because XGBoost models are based on an ensemble of decision trees, it facilitated the model’s interpretation, which provided a relevant additional result, the features’ importance in the forecasting.
- Exploring user-generated content for improving destination knowledge: the case of two world heritage citiesPublication . António, Nuno; Correia, Marisol B.; Ribeiro, Filipa PerdigãoThis study explores twoWorld Heritage Sites (WHS) as tourism destinations by applying several uncommon techniques in these settings: Smart Tourism Analytics, namely Text mining, Sentiment Analysis, and Market Basket Analysis, to highlight patterns according to attraction, nationality, and repeated visits. Salamanca (Spain) and Coimbra (Portugal) are analyzed and compared based on 8,638 online travel reviews (OTR), from TripAdvisor (2017–2018). Findings show that WHS reputation does not seem to be relevant to visitors-reviewers. Additionally, keyword extraction reveals that the reviews do not di er from language to language or from city to city, and it was also possible to identify several keywords related to history and heritage; in particular, architectural styles, names of kings, and places. The study identifies topics that could be used by destination management organizations to promote these cities, highlights the advantages of applying a data science approach, and confirms the rich information value of OTRs as a tool to (re)position the destination according to smart tourism design tenets.
- Uma abordagem metodológica para a análise comparativa de comentários de viagens online de duas cidades património da UNESCO – Coimbra (Portugal) e Salamanca (Espanha)Publication . Alexandre ribeiro, Filipa; António, Nuno; Correia, Marisol B.Apresenta-se uma proposta metodológica para a análise comparativa de comentários de viagens on-line (CVO), ao nível do destino e da língua. Optou-se por uma abordagem exploratória das cidades universitárias e património mundial da UNESCO (Coimbra, Portugal; Salamanca, Espanha), assumindo como ponto de partida que a classificação da UNESCO e as universidades medievais são fatores (1) comparáveis e (2) fundamentais para a atração de turistas. Com base na recolha de 8.638 CVO publicados no TripAdvisor em português, espanhol e inglês (2017-2018) sobre dez locais de cada cidade, propõe-se uma metodologia mista de técnicas de análise quantitativa e qualitativa. Concluiu-se que a reputação UNESCO não parece ser relevante para os visitantes-comentadores; são, contudo, distintos os aspetos realçados, de acordo com a língua. Este estudo permite destacar as vantagens da aplicação de vários métodos de análise num estudo comparativo e demonstrar a riqueza informacional dos CVO como instrumento para (re)posicionar o destino.
- Software as a service: an effective platform to deliver holistic Hotel Performance Management systemsPublication . António, Nuno; Serra, FranciscoThis study main objective was to assess the viability of development of a Performance Management (PM) system, delivered in the form of Software as a Service (SaaS), specific for the hospitality industry and to evaluate the benefits of its use. Software deployed in the cloud, delivered and licensed as a service, is becoming increasingly common and accepted in a business context. Although, Business Intelligence (BI) solutions are not usually distributed in the SaaS model, there are some examples that this is changing. To achieve the study objective, design science research methodology was employed in the development of a prototype. This prototype was deployed in four hotels and its results evaluated. Evaluation of the prototype was focused both on the system technical characteristics and business benefits. Results shown that hotels were very satisfied with the system and that building a prototype and making it available in the form of SaaS is a good solution to assess BI systems contribution to improve management performance.