Assessing determinants of desirable ES impact on end-user jobs

To increase the likelihood of experts systems' success it is useful to identify the more important determinants to focus managerial attention and resources. Seven major determinants of expert system success, here defined as desirable impact of the system on users' jobs, have been identified from the literature. DuPont's collection of expert systems (ES) provided the sample of 114 applications used in this study. The results corroborate much of what has been proposed in the literature, except for user characteristics which have been found to have no significant relationship to the measure of success. Based on the results, some recommendations are made to expert system development managers, including: (1) besides the recommendations already proposed in the literature, managers should deliberately seek to deal with important, large, labour intensive and complex problems which are important to the organization; (2) the selection of a development shell with the characteristics described in this study, and which matches the problem at hand is an important determinant of success; and (3) even though the primary source of knowledge is one or more domain experts, user involvement in the development process remains an important factor for ES to have a desirable impact on the latter's jobs.