engleski

An Integrated Intelligent System for Data Mining and Decision Making

A widespread proliferation of databases has created demand for powerful tools for turning stored data into useful knowledge. Analytical and predictive capabilities of data mining tools form the basis of business decision support systems. The paper explicates a novel data classification environment designed for real-world business problems that exhibit a high degree of undeterministic behavior. The environment is implemented in Java and uses SQL queries for direct database access. It employs a variation of Naive Bayes algorithm augmented with attribute selection for eliminating redundant attributes. Target concept is described using C4.5 decision tree generator. An embedded visual performance evaluation tool enables significantly faster convergence towards the final model. The predictive power of the classification environment is illustrated on a typical business problem.

Data mining; Knowledge discovery; Decision making

nije evidentirano