Quantitative WinWin: a new method for decision support in requirements negotiation
SEKE '02 Proceedings of the 14th international conference on Software engineering and knowledge engineering
An Efficient Boosting Algorithm for Combining Preferences
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Case-based ranking for decision support systems
ICCBR'03 Proceedings of the 5th international conference on Case-based reasoning: Research and Development
Toward case-based preference elicitation: similarity measures on preference structures
UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
| Hi-index | 0.00 |
Preference elicitation is a well known bottleneck that prevents the acquisition of the utility function and consequently the set up of effective decision-support systems. In this paper we present a new approach to preference elicitation based on pairwise comparison. The exploitation of learning techniques allows to overcome the usual restrictions that prevent to scale up. Furthermore, we show how our approach can easily support a distributed process of preference elicitation combining both autonomy and coordination among different stakeholders. We argue that a collaborative approach to preference elicitation can be effective in dealing with non homogeneous data representations.The presentation of the model is followed by an empirical evaluation on a real world settings. We consider a case study on environmental risk assessment to test with real users the properties of our model.