A Classification of the Simulation Log Set by DEA

Abstract

This study proposes a method of using Data Envelopment Analysis (DEA) to classify a set ofinput/output logs in a social or organizational simulation and compares it with previous methods based oncluster analysis using examples. DEA is used mainly in policy analysis as a method to compare theefficiency based on multiple input and multiple output data. In DEA, the entire data is partitioned by thedata that define efficiency corner points, called reference sets. In this study, we propose to use DEA as aclassifier of simulation logs due to this property of reference sets. In this paper, we illustrate how DEAallows us to classify a set of simulation logs by their characteristics, using the SIR model of infectiousdisease spreading with additional variables multiple indicating measures. In addition, the results werecompared with the results of the previous log classification using cluster analysis.