CAES: A model of an RBR-CBR course advisory expert system

Academic student advising is a gargantuan task that places heavy demand on the time, emotions and mental resources of the academic advisor. It is also a mission critical and very delicate task that must be handled with impeccable expertise and precision else the future of the intended student beneficiary may be jeopardized due to poor advising. One integral aspect of student academic advising is course registration, where students make decisions on the choice of courses to take in specific semesters based on their current academic standing. In this paper, we give the description of the design, implementation and trial evaluation of the Course Advisory Expert System (CAES) which is a hybrid of a rule based reasoning (RBR) and case based reasoning (CBR). The RBR component was implemented using JESS. The result of the trial experiment revealed that the system has high performance/user satisfaction rating from the sample expert population conducted.