A Learning-Enhanced Adaptive Decision Support System Framework

Abstract

Knowledge plays an important role in knowledge-based decision support systems (DSS). This is especially salient in dynamic environments where knowledge-based adaptive DSS operate. The role played by these DSS necessitates maintaining knowledge current since stale knowledge could lead to poor decision support. We present a generic adaptive DSS framework with learning capabilities that continually monitors itself for possible deficit in the knowledge base, expired or stale knowledge already present in the knowledge base, and availability of new knowledge from the environment. The knowledge base is updated through incremental learning. We illustrate the proposed generic knowledge-based adaptive DSS framework using examples from three different application areas. The framework is flexible by being able to be modified or extended to accommodate the idiosyncrasies of the application of interest. The proposed framework is an example artifact that naturally satisfies the design science guidelines. Moreover, by iteratively improving its performance through interactions and feedback from users, it also serves to bridge behavioral science and design science paradigms.