Using data mining to support the construction and maintenance of expert systems

Many expert systems are constructed from and allied with a large collection of databases that are continually being updated. The authors address the issues of how such a knowledge base can be constructed using tools that search the databases for significant, unexpected correlations and present them to the knowledge engineer for review. Once a knowledge base has been constructed, there is the problem of keeping it consistent with changing conditions in the real world. Concepts which are embodied in the data may drift in time, and so some mechanism for updating the knowledge base must be developed. As it would prove too costly to periodically revisit the knowledge acquisition phase, the authors propose to monitor the domain database automatically for significant concept change