Um processo para o desenvolvimento experimental de aplicações de data mining e data science alinhadas ao planejamento estratégico da organização

• Ano de defesa: 2021
• Autor(a) principal: Cruz, Rodrigo Fontes
• Orientador(a): Rodrigues Júnior, Methanias Colaço
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Programa de Pós-Graduação: Pós-Graduação em Ciência da Computação
• Palavras-chave em Português: Mineração de dados (Computação); Estrutura de dados (Computação); Recuperação de dados (Computação); Data mining; Data science; Alinhamento estratégico
• Palavras-chave em Inglês: Data analytics; Experimentação; Strategic alignment; Experimentation
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://ri.ufs.br/jspui/handle/riufs/14561

Context: The Big Data phenomenon has imposed maturity on companies in the exploration of their data, as a prerogative to obtain valuable insights about their customers and the power of analysis to guide decision making. In this way, a general approach that describes how to extract knowledge for the execution of the business strategy needs to be established. Goal: The objective of this work is to develop and evaluate a process of development of Data Mining and Data Science applications directed to the strategy and evaluated experimentally. Method: Initially, a Quasi-Systematic Review of the literature was carried out, with the purpose of identifying and characterizing the methods of developing BI (Business Intelligence) and Data Mining applications directed to the strategy or that provide for Experimental evaluation. Finally, a case study was carried out at a federal educational institution, with the objective of introducing and evaluating the developed process. Results: The Literature Review evidenced the absence of a complete approach to discipline strategic alignment and experimentation, providing clear compliance with strategic objectives and an experimental phase in the validation of results. The case study brought positive initial evidence that it is possible to discipline and align the development of Data Mining and Data Science applications to the organization's strategic planning, as well as to encourage the use of the scientific method in this context. Conclusion: A BI methodology directed to the strategy can be extended to the contemplation and development of Data Mining and Data Science applications evaluated experimentally.