Journal article

Performance evaluation of consumer decision support systems

Consumer decision support systems (CDSSs) help online users make purchasing decisions in e-commerce Web sites. To more effectively compare the usefulness of the various functionalities and interface features of such systems, we have developed a simulation environment for decision tasks of any scale and structure. Furthermore, we have identified three criteria in an evaluation framework for assessing the quality of such CDSSs: users' cognitive effort, preference expression effort, and decision accuracy. A set of experiments carried out in such simulation environments showed that most CDSSs employed in e-commerce Web sites are suboptimal. On the other hand, a hybrid decision strategy based on four existing ones was found to be more effective. The interface improvements based on the new strategy correspond to some of the advanced tools already developed in the research field. This result is therefore consistent with our earlier work on evaluating CDSSs with real users. That is, some advanced tools do produce more accurate decisions while requiring a comparable amount of user effort. However, the simulation environment enables us to efficiently compare more advanced tools among themselves, and indicate further opportunities for functionality and interface improvements

Related material


EPFL authors