APPLICATION OF THE DISTRIBUTED DATA MINING USING CLUSTERING K-MEANS IN THE PREDICTABILITY OF THE REQUEST PROCESS OF A PUBLIC ORGANIZATION

• Autores: Mamani Rodríguez, Zoraida, Del Pino Rodríguez, Luz, Cortez Vasquez, Augusto
• Formato: artículo
• Fecha de Publicación: 2017
• Institución: Universidad Nacional Mayor de San Marcos
• Repositorio: Revistas - Universidad Nacional Mayor de San Marcos
• Lenguaje: español
• OAI Identifier: oai:ojs.csi.unmsm:article/13949
• Enlace del recurso: https://revistasinvestigacion.unmsm.edu.pe/index.php/idata/article/view/13949
• Nivel de acceso: acceso abierto
• Materia: Distributed Data Mining; Clustering Algorithm; K-means; Petition; Minería de Datos Distribuida; Algoritmo Clustering; petitorio

Distributed data mining is contemplated in the field of research and involves the application of the process of extracting knowledge about large volumes of information stored in distributed databases. Modern organizations require tools that perform tasks of prediction, forecasting, classification and others, online, on their databases that are located in different nodes interconnected through the Internet, in a way that allows them to improve the quality of their services. Clustering is one of the main modeling techniques of data mining which consists of dividing the information into different groups, internally the members of each group are very similar to each other and dissimilar to the members of the other groups. The resulting clusters or clusters allow us to predict patterns of behavior that can contribute to organizational decision-making. It is in this context that the present work elaborates a proposal of a prototype of application of distributed data mining based on the k-means technique in the predictibilidad of the request process of a public organization.