Antecipação de Mudança de Regimes na Fatia Diária de Voos Atrasados e Cancelados no Aeroporto Internacional de Guarulhos

• Ano de defesa: 2019
• Autor(a) principal: Teixeira, Rosana Batista [UNIFESP]
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de São Paulo (UNIFESP)
• Palavras-chave em Português: Change Point Detection; Hidden Markov Model; Classification.; Detecção De Pontos De Mudança; Modelos Escondidos De Markov; Classificação.
• Link de acesso: https://sucupira.capes.gov.br/sucupira/public/consultas/coleta/trabalhoConclusao/viewTrabalhoConclusao.jsf?popup=true&id_trabalho=7928485; https://repositorio.unifesp.br/handle/11600/59943

Flight delays and cancellations are frequent occurrences in most airports around the world. In Brazil the deregulated increase in air traffic caused flight concentration in some airports, enabling the occurrence of delays and cancellations due to congested days. The Guarulhos International Airport is the most affected by delays. Therefore, the goal of this work is to anticipate the occurrence of congested days at Guarulhos International Airport employing clustering and classification approaches to identify a regime change in the daily share of delayed and canceled flights. The built model is composed of a Hidden Markov Models as a clustering approach and the classification methods Classification and Regression Tree, Random Forest, and Support Vector Machine. The accuracy of the prediction model was considered satisfactory, and it anticipates the regime change in a daily share for one period ahead.