Open Collections

Distributed case management : a concept for decision support systems

University of British Columbia

This thesis suggests a new perspective for Decision Support Systems (DSS) that is guided by the dominant role of experience in decision making. Evidence from cognitive research supports the view that organizational problem solvers rely to a large extent on using episodic knowledge gained from similar problem solving experiences, rather than by starting from first principles every time. In addition, people tend to cooperate and seek other's experience, especially as task domains become more complex and relevant knowledge becomes more sparse. Case-Based Reasoning (CBR) has gained much appeal by utilizing previous decision making results to aid in current problem solving activities. However, existing models do not support the exchange of case-based experiences (i.e. learning from others' experience) among organizational workers. Humans are also more flexible in problem solving than existing CBR models in that they can draw analogies from various, related domains, rather than just from within one domain. Derived from both analogical reasoning (AR) and CBR methods, a DSS model based on the concept of Distributed Case Management (DCM) is proposed that would facilitate the exchange of computer-mediated experiences among organizational workers. The feasibility of this approach is demonstrated by implementing a distributed retrieval mechanism based on an analog retrieval algorithm called Analog Retrieval by Constraint Satisfaction (ARCS).

Thesis/Dissertation

application/pdf

2008-12-16

For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.

http://hdl.handle.net/2429/2977

Business Administration

University of British Columbia

UBCV

DSpace