Automatic revision of qualitative multi-attribute decision models

Data-driven revision of decision models is defined as follows: given an existing model and a set of data items, revise the model to match the data items. In this paper, we propose and experimentally evaluate a method for the revision of qualitative hierarchical multi-attribute models in DEX methodology. A possible improvement of the method with heuristic approach is also proposed and evaluated. The revision method is automatic, but limited to the modification of utility functions. Using a simple experimental model and simulated data, we show that the method is valid and that it improves the classification accuracy of the models.