Research On AP Cluster Technology Oriented To Enterpirse Competitive Intelligence System

With the development of information technology, the data resources of enterprise isgrowing explosively. The traditional competitive intelligence system exposes itsdeficiencies of the data collection and processing. However, the rise of data miningprovides a new impetus for Enterprise Competitive Intelligence System. Fuzzy clusteranalysis is an important research topic in data mining and widely applied in variousfields. Therefore, the research on fuzzy cluster analysis in the Enterprise CompetitiveIntelligence System is of great significance.With the application in Enterprise Competitive Intelligence System, this papermade the following improvements for the problems of AP (affinity propagationclustering algorithm):For the problem that the effect of AP algorithm applied in complex dataset is notgood, this paper proposed an improved algorithm. At the same time, when use someinformation to optimize the result of clusters, we proposed a method namedS-AP(Semi-supervised affinity propagation clustering).For the problem thatcharacteristics of each dimension has different contributions in course of clustering, thispaper proposed an improved AP algorithm which is based on features weighted. Thealgorithm extracted main feature vectors using principal component analysis, and gavecorresponding objective weight. Besides, it feature weighted sample date according tothe given subjective weight, and clustered the weighted data using the improved APalgorithm.Finally, based on the previous research and according to projects before, weintroduced an improved AP algorithm to the Enterprise Competitive Intelligence System,which achieved better results.