Towards Identifying Multicriteria Outliers: An Outranking Relation-Based Approach

This article tackles the problem of outlier detection in the multicriteria decision aid (MCDA) field. The authors propose an outlier detection method based on binary outranking relations and Local Outlier Factor (LOF) algorithm. The outlier is detected by applying LOF algorithm on the distribution of the outranking relations generated by a multicriteria outranking method. The proposed approach is illustrated on an artificial example and evaluated on a real life financial problem, the country risk problem.