The production from collaborative web content has grown in recent years. Thus, exploring the quality of these data repositories has also become relevant. This work proposes to develop a tool called WebFeature. Such system allows one to manage, extract, and share quality related feature sets from text, graph and article review. To accomplish this, diff erent types of metrics were implemented based on structure, style, and readability of the texts. In order to evalu- ate the WebFeature applicability, we presented a scenario with its main functionalities (creation of a feature set, extraction of features from a known dataset, and publishing the feature set). Our demon- stration shows that this framework can be useful for extracting features automatically, supporting quality prediction of collabo- rative contents, analyzing text characterization, and improving research reproducibility.
Realizar operações na bolsa de valores é uma tarefa complexa, uma vez que alterações nos mais diversos setores acabam impactando o mercado acionário e, por isso, diversos estudos na área de inteligência artificial abordam esse tema com o propósito de facilitar operações. Esse artigo visa apresentar diferentes estratégias apoiadas pelo uso de algoritmos baseados em aprendizado supervisionado com o intuito de criar um ambiente propício à apreciação do capital. Foram trabalhadas três estratégias para quatro ativos de segmentos diferentes listados na B3 entre 2009 e 2021. Foi adotado o modelo LSTM como o algoritmo para previsão de valores futuros a partir das séries temporais do mercado e seus indicadores. Os resultados apontam que a estratégia proposta pode gerar lucro em mais de 70% das operações, obtendo um retorno geral maior que outros investimentos utilizados como comparação, considerando aportes entre os anos entre os anos de 2012 e 2021.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.