Coleção de Artigos Acadêmicos
URI permanente para esta coleçãohttps://repositorio.insper.edu.br/handle/11224/3227
Navegar
4 resultados
Resultados da Pesquisa
Artigo Científico Validação de modelos de machine learning por experimentos estatísticos de campo(2024) Toaldo, Alexsandro; Vallim Filho, Arnaldo Rabello de Aguiar; Oyadomari, José Carlos Tiomatsu; Mendonça Neto, Octavio Ribeiro deObjetivo – Este artigo apresenta uma aplicação prática com o desenvolvimento de um experimento estatístico de campo em uma indústria de latas premium de alumínio nos Estados Unidos, visando validar estatisticamente resultados de modelos de machine learning (ML), previamente construídos. Metodologia: Usou-se conceitos de pesquisa intervencionista, que envolve experimentos de campo onde pesquisador e organização anfitriã atuam em conjunto buscando experimentar no sistema em estudo, e por meio da observação gerar conhecimento. Originalidade/Relevância: Sobre originalidade, não é frequente na literatura modelos de ML validados por experimento planejado de campo, seguido de análise estatística rigorosa. E a relevância da proposta se deve à sua contribuição para a literatura e pelas possibilidades de replicações do estudo em escala maior, na própria empresa ou em qualquer outra com desafios similares. Principais Resultados: Em fase anterior do estudo modelos de ML identificaram as variáveis de maior impacto em ineficiências (geração de sucata) em um processo de produção de latas de alumínio. Essas variáveis foram validadas nesta fase do estudo, através de experimento estatístico de campo, confirmando a significância estatística dos resultados do modelo de ML. Contribuições Teóricas e Práticas: A pesquisa contribui em termos práticos e científicos, pois a validação estatística de modelos de ML por experimentos planejados de campo é uma contribuição para a literatura de ciência aplicada, além de usas possibilidades práticas. Da mesma forma, apesar de amplamente utilizadas em diferentes áreas, pesquisas de cunho intervencionista ainda apresentam lacuna importante nas ciências sociais aplicadas, principalmente na gestão de processos industriais.Artigo Científico Implementing total quality management in a virtual organisation: thoughts and lessons from an interventionist approach(2024) Carneiro, Welington Norberto; Mendonça Neto, Octavio Ribeiro de; Oyadomari, Jose Carlos Tiomatsu; Dultra-de-Lima, Ronaldo GomesPurpose – This article aims to understand the challenges and key takeaways of implementing total quality management (TQM) in a virtual organisation. Design/methodology/approach – An interventionist research (IVR) methodology combined with a qualitative critical event analysis was used to evaluate the challenges and concerns faced during the company’s adoption of TQM and understand the roles of the key players involved. Findings – Standard process tools such as desktop procedures (DTP), focused teams, and service-level agreements (SLAs) were fundamental to implementing TQM in the company. These processes require the right leaders, but external agents may also be influential, acting as accelerators of change in adopting and using management practices in small companies. Indeed, the researcher acted as a problem solver, bringing innovative solutions to the firm using a hands-on iterative approach. Practical implications – This research underscores the importance of critical success factors (CSF), such as employee engagement, training, and project management tools. These factors are not just important but crucial for the success of TQM in organisations seeking to adopt the industry’s best practices. Originality/value – This study, conducted as a virtual IVR for TQM implementation, provides novel insights for practitioners and academics. It elucidates the pivotal role of some quality management tools in the journey towards TQM and the role of both internal and external critical players in the process, particularly in small virtual organisations based on innovative business models.Artigo Científico Trials of strength, paradoxes and competing networks in kaizen institutionalization(2024) Carneiro, Welington Norberto; Oyadomari, Jose Carlos Tiomatsu; Afonso, Paulo; Dultra-de-Lima, Ronaldo Gomes; Mendonça Neto, Octavio Ribeiro dePurpose – This paper seeks to understand kaizen in practice as it travels through time and space in the organisational setting. Design/methodology/approach – A qualitative case study was carried out at a multinational company using mainly interviews for the data collection that were analysed from an actor-network theory (ANT)perspective. Findings –This paper finds that the company deals with a series of paradoxes while managing the kaizen process. Efficiency and quality paradoxes are the basis for starting kaizen projects. Furthermore,intrinsic, and extrinsic motivation, emerge in these processes, and paradoxes relate to how spontaneous ideas emerge in a deliberated context of cost-saving objectives. The supply chain finance team coordinates kaizen projects with the collaboration of plant managers, promoting the paradox of autonomy and control. In addition, as kaizen mobilises and enrols the actors, some trials of strength emerge, showing actors who oppose the kaizen network and create competing networks that mutually exist in the firm. Practical implications – This study presents valuable insights for professionals to successfully implement kaizen methodologies that take advantage of developing a network for problem-solving in organizations. Originality/value – This study highlights the supply chain finance team’s role in enrolling the actors within a network built by practitioners engaged in kaizen projects. Usually, engineers, quality, or manufacturing teams lead kaizen projects, and only occasionally, accounting and financial teams participate, including multidisciplinary teams.Artigo Científico Determinant factors of banking proftability: an application of quantile regression for panel data(2024) ADRIANA BRUSCATO BORTOLUZZO; Ciganda, Rodrigo Ricardo; Bortoluzzo, Mauricio MesquitaThis study examines the determinants of bank proftability using a quantile regression approach, ofering insights into factors afecting banks across diferent percentiles of proftability. Utilizing a comprehensive database from Orbis covering 1200 top-market institutions across 101 countries, the research uniquely employs dynamic panel quantile regression while addressing sample survival bias. Our fndings highlight that bank size and capital adequacy nega tively impact proftability, whereas market value exerts a positive infuence on higher proftability banks. Credit risk afects proftability diferently across levels of proftability, and infation rate shows signifcance only for higher proft ability banks. The study contributes to the existing literature by ofering valuable insights into the factors determining bank proftability and how they behave at diferent percentiles in the sample, suggesting the importance of bank efciency and competition in promoting economic growth