Intelligent agent assisted decision support for family financial planning


Student thesis: Master's Thesis

View graph of relations


  • Shijia GAO

Related Research Unit(s)


Awarding Institution
  • Huai Qing WANG (Supervisor)
Award date3 Oct 2005


Today, more people than ever recognize the importance of managing and controlling their family finances. In current financial markets characterized by constantly changing tax laws and increasingly complex transactions, the demand for family financial planning (FFP) services is rising dramatically. FFP can help the wealthy to spend and invest wisely. FFP can also help those with inadequate income to take steps to control their financial situation and lead to an improved lifestyle. Among the rewards of FFP are improved standard of living, wise spending patterns, and increased wealth. However, the current available FFP resources and practices have many limitations. In particular, the trend to develop advisory systems that focus mainly on the financial or investment side fails to consider the whole picture of FFP. Separating financial and investment advice from legal and accounting advice may result in conflicting advice or important omissions that could lead to users suffering financial loss. In order to solve the problems, intelligent agent assisted decision support for FFP has been investigated in this research. It consists of three interrelated components. The first component depicts the conceptual models for FFP, including the more general and high-level FFP decision making process model (Gao et al., 2005b), and the derived FFP semantic schema. The FFP semantic schema not only contains the overall FFP knowledge representations (both domain level and token level), but also comprises of detailed individual domain level models that specifies each class’ attributes and activities. The impacts of the comprehensive models provide a solid framework for FFP development practice, which guide the analysis, design, and development for FFP. The application of our models can lead to unambiguous understanding of the concepts of FFP. The second component covers design and development of a Web-services-agent-based FFP prototype, Intelligent FFP Decision Support System (IFFPS) (Gao et al., 2004a; 2004b; 2005a; 2005b). Agent technology is applied to deal with the complex, dynamic, and distributed FFP process; Web-services techniques are proposed for more inter- operability and scalability in network-based business environment. By integrating agent technology with Web-services to make use of the advantages from both, this approach provides a more intelligent, flexible, autonomous, and comprehensive solution to FFP. The third component investigates our proposed system effectiveness via a laboratory experiment (Gao et al., 2005b). The results show that our proposed solution outperforms the traditional FFP system in terms of higher decision outcome quality, more effective decision process, and better user perception. This cross-discipline practice provides a scientific method to evaluate the DSS effectiveness. The major contributions of this research are the theoretical investigation of the FFP decision making process and the innovative approaches for the development of intelligent agent assisted decision support for FFP. Our research started from the high-level conceptual modeling of the domain knowledge; on basis of the knowledge representation and in-depth understanding of the FFP domain, we then developed the system architecture; and system design architecture derives the implementation architecture, which is easily converted to programming codes; finally we evaluated the system effectiveness empirically. We believe our research approach and findings will lead to a new stage of technology-mediated financial decision support. The results of this study highlight the fact that the important concepts, including the conceptual model, the agent and Web-services technologies, and the architectural considerations required for developing a financial application, which can assist financial decision making.

    Research areas

  • Decision support systems, Finance, Personal, Intelligent agents (Computer software)