Abstract-Among various statistical and data mining discriminant analysis proposed so far for group classification, linear programming discriminant analysis have recently attracted the researchers' interest. This study evaluates mult i-group discriminant linear programming (MDLP) for classificat ion problems against well-known methods such as neural networks, support vector machine, and so on. MDLP is less complex co mpared to other methods and does not suffer fro m local optima. However, somet imes classification becomes infeasible due to insufficient data in databases such as in the case of an Internet Service Prov ider (ISP) small and med iu m-sized market considered in this research. This study proposes a fuzzy Delphi method to select and gather required data. The results show that the performance of MDLP is better than other methods with respect to correct classification, at least for small and medium-sized datasets.

Organizational decisions involve with unusually vague and conflicting criteria. This controversy increases empirical uncertainties, disputes, and the resulting consequences of these decisions. One possible method in subduing this problem is to apply quantitative approaches to provide a transparent process for resolute conclusions which enables decision makers to formu late accurate and decisive on time decisions. Although numerous methods are presented in the literature, the majority of them aim to develop theoretical models. However, this article aims to develop and implement an integrated fuzzy virtual MCDM model based on fuzzy AHP and fuzzy TOPSIS as a decision support system (DDS). Preventing disadvantageous face-to-face decision-making by achieving positive benefit fro m virtual decision making causes the proposed DDS to be suitable for making crucial decisions such as supplier selection, employee selection, emp loyee appraisal, R&D project selection, etc. The proposed DDS has been imp lemented in an optical company in Iran.