A DEA-DA approach for classifying multi-group observations

Activity: Talk or presentation typesOral presentation


Data envelopment analysis-discriminant analysis (DEA-DA) exploits the methodological and analytical advantages of two models at once. DEA-DA identifies the overlap between two groups of observations(firms) along with determining the group classification of a newly sampled observation. However, it may be of interest to have more than two groups of observations in the analysis. In this paper, we propose a new DEA-DA technique for classifying an observed data set into several groups of observations. We additionally present the applicability of our approach by predicting the group membership of a set of suppliers that play a tremendous role in a sustainable supply chain.
Period17 Jul 2017
Event title21st International Federation of Operational Research Societies
Event typeConference
Conference number21
LocationQuébec City, Canada, QuebecShow on map
Degree of RecognitionInternational