Toward association rules based decision making in Lipski´s Incomplete Information Databases

We have been coping with several aspects of rough sets in Non-deterministic Information Systems (NISs). We are simply calling this work Rough Non-Deterministic Information Analysis (RNIA). This paper newly considers Lipski´s Incomplete Information Databases (LIIDs) which can be seen as NISs with intervals, and proposes new decision making in LIIDs. A granular computing concept is applied to intervals, and we define the validity of the decision by the minimum and the maximum of support and accuracy with respect to the association rule.