CIDA: the expert Company Information Database Adviser

Abstract

The development and testing of an expert system to assist with the selection of online business databases for UK company information is described. The Company Information Database Adviser (CIDA) was designed for novice and end- user searchers and covers seven categories of company infor mation : factual (directory) details, financial data, company news, company structure, mergers and acquisitions (M & A) activity, market information and company profiles. The devel opment tool was the Leonardo expert system shell. Knowledge acquisition included three knowledge elicita tion sessions with each of four experienced business informa tion intermediaries. Outputs of knowledge acquisition were: (i) factual and evaluative information for over 200 database/ host combinations, and (ii) rules, expressed diagrammatically, for database selection within each category of company infor mation. These were used to build a prototype which was examined by intermediaries and further refined. The design is outlined and the rules governing the selection of company directory databases are described by way of illustration. Test ing included: an evaluation of the user interface by novice users; field testing by staff and end-users at a prominent busi ness school, and comparative performance trials against conventional database directories. CIDA's database recom mendations were in close agreement with those of business intermediaries across a range of independently generated queries. It was used far more successfully than conventional business database directories by trainee searchers (library and information students). End-user field trials were disappoint ing because of lack of participation. The study concludes that expertise in business database selection can successfully be distilled into a number of rules which can be applied by an expert system, but more research is needed into how databases are selected and used.