Applying machine learning to model management in decision support systems

Model management systems have become increasingly important in handling complicated decision problems in decision support systems (DSS). Aiming at overcoming the weaknesses of currently used model management systems, we present a new framework of model management system which is capable of performing model manipulation more effectively. The new approach incorporates machine learning to acquire model manipulation knowledge, stored in the form of schemata, and to refine these acquired schemata. In addition, we also address two issues that have so far been overlooked in the DSS literature: (1) to refine existing model representations as more experiences are accumulated and (2) to create model selection heuristics adaptive to the DSS environment.