Implantação de metodologia de análise de dados em departamento de garantias
Збережено в:
| Автор: | |
|---|---|
| Дата публікації: | 2025 |
| Формат: | Master thesis |
| Мова: | por |
| Джерело: | Repositório Institucional da UPF |
| Download full: | https://repositorio.upf.br/handle/123456789/10004 |
Резюме: | The growing demand for faster, evidence-based decisions has driven organizations' interest in adopting a data-driven culture. This work proposes the application of the CRISP-DM methodology in a Warranty department of a company in the agricultural machinery sector, aiming to structure a data analysis process capable of improving information organization, generating reliable indicators, and supporting decision-making. The central motivation stems from the observation that, although data is available in systems such as ERP (Enterprise Resource Planning), its use is still limited by a lack of standardization, low integration between sources, and a lack of technical training among the team. The CRISP-DM methodology was adopted for its consolidated and iterative structure, suitable for dynamic organizational contexts, and each of its phases was executed in the project. The results demonstrate concrete progress: team training in Tableau, creation of analytical catalogs, construction of interactive dashboards, analysis of failure causes, and identification of temporal patterns in warranty requests. Furthermore, new demands were prioritized by the area, indicating greater maturity in relation to the data-driven approach. Based on the results achieved, it is proven that the application of the CRISP-DM methodology was effective in guiding all phases of the project, from understanding the business to implementing practical solutions. As a main contribution, this work demonstrates that it is possible to structure data analysis projects even in sectors with low maturity in data science, using a consolidated and iterative methodology such as CRISP-DM. This approach not only enabled relevant technical deliverables but also boosted the adoption of a data-driven culture in the Warranty department, serving as a model for future similar initiatives in other areas of the company. |