BOCR framework for decision analysis

This paper considers establishing a framework for modellig decision analysis problems where the analyst must cope with uncertainty, multiple objectives, multiple attributes and multiple actors. These probems rise when considering large scale and complex decision problems encountered in real world applications in domains such as risk assessment and managment, infrastrucutres planning, complex process monitoring, supply chain planning, etc. To tackle this modelling chalenges, we propose to use BOCR (benefit, opportunity, cost, and risk) paradigm to identify attributes that must characterize an alternative with regard to a given objective. Then Bayesian network and/or AHP (analytic hierrarchy process) analysis can be used to assess the values of these later attributes. Finally an aggregation method based on satisficing game is developed that permit to evaluate each alternative by two measures: selectability degree constructed using “positive” attributes (benefit and opportunity) and the rejectability degree built on “negative” attributes (cost and risk)