An emerging online business decision making architecture in a dynamic economic environment

Abstract

It is widely acknowledged that a corporate's profitability that decreases dramatically not only threatens both potential and current investors, but also can freeze stock market transactions as well as deteriorate the flow of economic resources. However, far too little attention has been paid to this issue, which also has been deemed as a main trigger for a financial crisis. To confront this problem, a decision support system can be built up to evaluate a corporate's operating performance. Thus, this study introduces a novel architecture for forecasting the online operating performance of a firm when entering data at different time intervals. The introduced architecture is grounded on multiple data envelopment analysis specifications, dynamic fuzzy c-means (DFCM), and extreme support vector machine (ESVM). Because obtaining a comprehensible architecture is essential for achieving high accuracy in today's knowledge-based economy, this study advances the opaque nature of the introduced architecture and extracts the inherent knowledge to represent it in a transparent, human-readable format. The decision logics can be judged or examined by users, which will increase the acceptance rate of the architecture as well as enhance its practical application. Our built-up architecture, tested by real cases, is a promising alternative for financial performance forecasting.