Repositório Coleção:
http://hdl.handle.net/10071/15084
2024-03-28T09:37:27ZApplying neural networks to the extraction of knowledge from accounting reports: A classification study
http://hdl.handle.net/10071/29448
Título próprio: Applying neural networks to the extraction of knowledge from accounting reports: A classification study
Autoria: Trigueiros, D.; Berry, R. H.
Editor: Robert R Trippi; Efraim Turban
Resumo: This study develops a new approach to the problem of extracting meaningful information from samples of accounting reports. Neural networks are shown to be capable of building structures similar to financial ratios, which are optimal in the context of the particular problem being
dealt with. This approach removes the need for an analyst to search for appropriate ratios before model building can begin.1993-01-01T00:00:00ZLearning by exchanging advice
http://hdl.handle.net/10071/29250
Título próprio: Learning by exchanging advice
Autoria: Oliveira, E.; Nunes, L.
Editor: Nikhil Ichalkaranje; Lakhmi C. Jain; Rajiv Khosla
Resumo: The emergence of Multiagent systems brought new challenges to the field of Machine Learning, as it did to many others. One of the main challenges is to take advantage of the information available when
several agents, possibly using different learning techniques, are dealing with similar problems, either in the same location (i.e. acting as a team) or in different ones. This work aims at studying the possible advantages and pitfalls of exchanging information during the learning process, leading to better adaptation. We will discuss the subject of when, how and to whom ask for advice, and present the
results obtained in two experimental scenarios: the Pursuit (Predator-Prey) Domain and a Traffic Control simulation. Results show that exchange of information can improve the average performance of learning agents enabling them to escape from local maxima in some cases, although it may reduce the exploration of the space, preventing successful agents from finding better local maxima of the quality function.2005-01-01T00:00:00ZData mining and predictive analytics for E-tourism
http://hdl.handle.net/10071/29001
Título próprio: Data mining and predictive analytics for E-tourism
Autoria: Antonio, N.; de Almeida, A.; Nunes, L.
Editor: Zheng Xiang; Matthias Fuchs; Ulrike Gretzel; Wolfram Höpken
Resumo: Computers and devices, today ubiquitous in our daily life, foster the generation of vast amounts of data. Turning data into information and knowledge is the core of data mining and predictive analytics. Data mining uses machine learning, statistics, data visualization, databases, and other computer science methods to find patterns in data and extract knowledge from information. While data mining is usually associated with causal-explanatory statistical modeling, predictive analytics is associated with empirical prediction modeling, including the assessment of the quality of the prediction. This chapter intends to offer the readers, even those unfamiliar with this topic, a general overview of the key concepts and potential applications of data mining and predictive analytics and to help them to successfully apply e-tourism concepts in their research projects. As such, the chapter presents the fundamentals and common definitions of/in data mining and predictive analytics, including the types of problems to which it can be applied and the most common methods and techniques employed. The chapter also explains what is known as the life cycle of data mining and predictive analytics projects, describing the tasks that compose the most widely employed process model, both for industry and academia: the Cross-Industry Standard Process for Data Mining, CRISP-DM.2022-01-01T00:00:00ZBlended learning compared to online learning in business, management, and accounting education: A bibliometric analysis and literature review
http://hdl.handle.net/10071/28996
Título próprio: Blended learning compared to online learning in business, management, and accounting education: A bibliometric analysis and literature review
Autoria: Santos, M.
Editor: Luísa Cagica Carvalho; Pedro Pardal
Resumo: The journey of business, management, and accounting education over the past decades included several teaching methods which may nowadays be considered outdated for the modern students who live, learn, and connect through technology. This study clusters the academic literature addressing online learning and b-learning applied to educational and training in the business, management, and accounting. Through the collection of all the relevant publications in Scopus, this study uses automated text mining techniques in VOSviewer software for comparing the evolution overtime of the online and blended methods in the context of scientific knowledge production. The results unveil that online-learning-related literature is grouped in nine clusters, instead of the seven clusters in case of blended learning, meaning that the first is more disperse in terms of topics. An in-depth analysis of the studies most closely related to each cluster's terms allow the authors to provide critical reflections that help professionals when choosing the accurate method and also the academics in identifying future research agendas.2022-01-01T00:00:00Z