Modelo de análise de predição do desenvolvimento das micro e pequenas empresas utilizando cadeias de Markov

• Ano de defesa: 2018
• Autor(a) principal: SILVA, Auristela Maria da
• Orientador(a): CAVALCANTI, André Marques
• Banca de defesa: CAVALCANTI, André Marques, MELO, André de Souza, RAMOS, Francisco de Sousa
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal Rural de Pernambuco
• Programa de Pós-Graduação: Programa de Pós-Graduação em Administração e Desenvolvimento Rural
• Departamento: Departamento de Administração
• País: Brasil
• Palavras-chave em Português: Microempresa; Análise de predição; Cadeias de Markov
• Área do conhecimento CNPq: OUTROS::ADMINISTRACAO RURAL
• Link de acesso: http://www.tede2.ufrpe.br:8080/tede2/handle/tede2/7221

Micro and small enterprises (SMEs) are constantly challenged in their ability to react to market threats and generate opportunities. Innovation emerges as a way to make these companies more robust and competitive. In this research, we will present a probabilistic model that contributes to the study of the dynamics of the behavior of MPE in relation to its innovative and organizational profile in the long term. The model used corresponds to a Markov Chain in discrete time, which in defining the maturity levels (states) of the companies and obtaining the probabilities of transition in a step, allows to describe and predict the future states of these organizations. The different states used are based on the Degree of Organizational Development (GO) and Degree of Innovation (GI), obtained from the Project Local Innovation Agents of the Brazilian Service of Support to Micro and Small Companies. To validate the model, a directed sample distributed in three groups of 20 companies from the food, furniture and clothing industry sectors of the state of Pernambuco will be used. The results indicate that, given the initial state of these companies, which are mostly at a level of management and innovation considered to be insipient, they will remain in reaching the steady state of the model.