Validation of a knowledge-based system: the ICE case

The authors present results from a validation study conducted on a knowledge-based system called ICE (Information Center Expert). The ICE system was developed to determine the software requirements of end-users and make appropriate recommendations. It incorporates the expertise of consultants from IBM/Endicott, IBM Tucson and the Center for the Management of Information (CMI) at the University of Arizona. It is found that the performance of ICE is comparable to that of the consultants at CMI. It is noted that the real use for ICE is as a front end to the consulting process that will enable CMI consultants to restrict their efforts to exceptional cases, i.e. cases that are not adequately covered by the ICE system. This alteration to the consulting process would enhance the effectiveness of the software selection process for users and also prove helpful to the consultants by reducing the number of situations requiring their attention. >