Knowledge-driven decision analytics for commercial banking

Although the corporate relationship manager seems to be the key enabler in commercial banking, the personal relationship sales model is not a sustainable model for the paradigm shift in digital financial markets. In this research, we propose a knowledge-driven decision analytics approach to improve the decision process. However, most of the corporate client documents processed in banks are not well-structured and the traditional analysis approach does not consider the document structure, which carries rich semantic information. We propose a document structure-based text representation approach with incorporating auxiliary information in the predictive analytics of unstructured data to improve the performance in the document classification task. The proposed approach significantly outperforms the traditional whole document approach which does not take into considerations of the document structure. With the proposed approach, knowledge can be effectively and efficiently used for business decisions and planning to improve the competitive advantage and substantiality of banks.