Computational Intelligence-Based Intelligent Business Intelligence System: Concept and Framework

Abstract

Decision making is an important task for enterprise managers, and is typically based on various data sources derived from information systems, such as enterprise resource planning, supply chain management and customer relationship management. Numerous business intelligence tools (BI) thus have been developed to support decision making. Some existing BI tools have several limitations, for example lacking data analysis and visualization capabilities. To increase the data analysis capability of BI tools, this study focuses on efficient data mining tools and presents an intelligent BI system framework based on many computational intelligence paradigms, including a predictor tool based on neuro-computing (cerebellar model articulation controller neural network, CMAC NN), a classifier tool based on neuro-computing (CMAC NN) and optimizer tools based on evolutionary computing and artificial life (such as real-coded genetic algorithm and artificial immune system). The predictor tool can be used to make predictions or conduct time series forecasting, the classifier tool can be applied to solve classification tasks, and the optimizer tools can be employed to optimize the parameter settings of the predictor and classifier tools. The proposed BI system can potentially be considered as an efficient data analysis tool for supporting business decisions.