Sistema inteligente basado en minería de datos para predecir la producción de fertilizante en la empresa Nutrition Vegetable Corporation Figal SAC
Cargando...
Fecha
2025
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Católica Santo Toribio de Mogrovejo
Resumen
En este estudio se desarrolló un sistema predictivo basado en minería de datos para la empresa Nutrition Vegetable Corporation Figal SAC, enfocado en optimizar su producción de fertilizantes mediante el análisis avanzado de datos históricos. Siguiendo la metodología CRISP-DM, se analizaron y evaluaron diversos modelos predictivos, aplicando técnicas de validación cruzada y métricas de rendimiento como precisión, exactitud y recall, donde la red neuronal alcanzó una capacidad predictiva del 53%. El sistema fue implementado a través de una interfaz web interactiva, validado bajo la norma ISO 25010, asegurando su usabilidad y eficiencia operativa en condiciones reales. Los resultados demostraron una mejora significativa en la planificación de la producción, evidenciada por la reducción de pérdidas operativas y una gestión más eficiente de recursos. La plataforma desarrollada permitió visualizar datos y generar predicciones en tiempo real, facilitando la toma de decisiones estratégicas y contribuyendo a prácticas más sostenibles en la cadena productiva, lo que posibilitó a la empresa anticipar y ajustar sus niveles de producción de manera más precisa, minimizando el desperdicio de recursos y mejorando su competitividad en el mercado. Las pruebas realizadas fueron llevadas a cabo mediante SonarCloud.
In this study, a predictive system based on data mining was developed for the company Nutrition Vegetable Corporation Figal SAC, focused on optimizing its fertilizer production through advanced analysis of historical data. Following the CRISP-DM methodology, various predictive models were analyzed and evaluated, applying cross-validation techniques and performance metrics such as precision, accuracy and recall, where the neural network reached a predictive capacity of 53%. The system was implemented through an interactive web interface, validated under the ISO 25010 standard, ensuring its usability and operational efficiency in real conditions. The results demonstrated a significant improvement in production planning, evidenced by the reduction of operational losses and more efficient resource management. The developed platform made it possible to visualize data and generate predictions in real time, facilitating strategic decision making and contributing to more sustainable practices in the production chain, which enabled the company to anticipate and adjust its production levels more precisely, minimizing the waste of resources and improving its competitiveness in the market. The tests carried out were carried out through SonarCloud.
In this study, a predictive system based on data mining was developed for the company Nutrition Vegetable Corporation Figal SAC, focused on optimizing its fertilizer production through advanced analysis of historical data. Following the CRISP-DM methodology, various predictive models were analyzed and evaluated, applying cross-validation techniques and performance metrics such as precision, accuracy and recall, where the neural network reached a predictive capacity of 53%. The system was implemented through an interactive web interface, validated under the ISO 25010 standard, ensuring its usability and operational efficiency in real conditions. The results demonstrated a significant improvement in production planning, evidenced by the reduction of operational losses and more efficient resource management. The developed platform made it possible to visualize data and generate predictions in real time, facilitating strategic decision making and contributing to more sustainable practices in the production chain, which enabled the company to anticipate and adjust its production levels more precisely, minimizing the waste of resources and improving its competitiveness in the market. The tests carried out were carried out through SonarCloud.
Descripción
Palabras clave
Minería de datos, Análisis predictivo, Fertilizantes, Data mining, Predictive analysis, Fertilizers
Citación
C. A. Seclen Custodio. "Sistema inteligente basado en minería de datos para predecir la producción de fertilizante en la empresa Nutrition Vegetable Corporation Figal SAC," tesis de licenciatura, Fac. de Ingeniería, Univ. USAT, Chiclayo, Perú, 2025. [En línea]. Disponible en:
