Article Preview
Top1. Introduction
Nowadays, companies have realized that improvements in competitiveness must be achieved by extending their focus to the purchasing function, which is increasingly considered by managers as a key strategic tool to achieve competitive advantage and to ensure the viability of the company. The success of manufacturing lies hugely on selecting best suppliers. An effective supplier selection model is a critical success factor for supply chains in a complex environment.
Uncertainty and imprecision are inherited in real life. Management of supply chain is a complicated process of stochastic and complicated events among different parts of a supply chain. Therefore, managing uncertainty is a main challenge within supply chain management. Vagueness or ambiguity are the main source of uncertainty (Tavana, 2014).
The supplier selection problem is obviously affected by the complexity and uncertainty due to the lack of information associated with related business environment in a global market. In recent years, it has seen a growing attention given in the field of uncertainty on the selection of suppliers with different criteria such as quality level, delivery, capacity, price and service.
Different supplier selection models have been developed by different scholars to deal with uncertainty in the field of supplier selection. These models are often developed using mathematical theories such as linear programming, nonlinear programming, multiple objectives linear and non-linear mathematical models, decision theory and game theory.
Due to the nature of supplier selection problem as a multi-objective decision problem, the multiple objectives programming (MOP) model was first introduced by weber and Ellram (1993) as a technique for selecting vendors in procurement environment characterized by multiple conflicting criteria. MOP models involve more than one objective regardless of whether there are goal target levels involved. The main aim of multi-objective programming is to assist a decision maker to choose a preferred solution among all the trade-offs. Its main advantages are that it is easy to implement, efficient and a very intuitive way to knowledge representation due to the ability of the human mind to comprehend it. MOP take the form of linear, integer, and mixed integer which have continuous, discrete, and both continuous and discrete solutions respectively.
In the literature, there are many researches that treat the mitigation of operational risks by developing various mathematical models but there is a shortage of models for addressing disruption risks. Disruptive events such as earthquakes, hurricanes and labor strikes have caused major damage to various companies.
The use of the Var and the CVaR techniques as optimization criteria in a multi-objective paradigm was first studied by Roman et al., (2007). These two risk measure have been widely used in financial engineering in the field of portfolio management. CVaR is used in conjunction with VaR. Uryasev (2000) and Rockafellar and Uryasev (2000, 2002) introduced a new approach to select a portfolio with the reduced risk of high losses. The portfolio is optimized by minimizing CVaR. This approach has been applied to solve supplier selection problem under disruption risk (Sawik (2011a, 2011b), Sawik (2013a, 2013b).