Modern Research in Decision Making

Abstract Due to the changes in the condition of every supply chain it is possible that the first optimal network design become inefficient .These changes can be caused by different reasons like changes in amounts or location of demands, changes in suppliers, costs, taxes, government regulations etc. So, it is necessary to redesign networks to obtain their new optimal configuration for adopting to new conditions. This paper proposes a new mathematical model for a multi-product supply chain network redesign problem. Since one of the main problems of real-world cases deals with is transportation, routing constraints in every echelon (plant to warehouse and warehouse to customer) are considered in the proposed model. In addition, a capacitated and heterogeneous fleet of transportation in a split delivery system is used to deliver demands of the first echelon to the warehouses and demands of the second echelon to customers. On the other hand, due to the production capacity of the manufacturers, some portions of demands is satisfied by outsourcing. The outsourced products are moved to the warehouses directly. The proposed model is validated through an illustrative example by some strong servers in a website which is used to solve the mathematical modeling problems. Then, some sensitive analysis are performed in order to investigate the effects of some key parameters on the optimal cost and figure of the network. Finally, we can reach the conclusion of need to consider the transportation and routing costs, and it is necessary to account outsourcing and some other costs and benefits in our redesign problems as well.

Abstract In this paper minimization of total tardiness with intermediate due dates in flow shop scheduling is presented. There are some situations in which there is a due date for each intermediate operation of a job such as research and development and consulting projects. Usually each project (job) is carried out through different phases (machines) and there is an associated due date for each phase. Thus the tardiness of each phase should be considered. Due to the complex nature of the tardiness in flow shop problems and since this problem is a NP-hard, three Meta heuristic approaches; Simulated Annealing, Genetic Algorithm and Particle Swarm Optimization have been applied to reach near optimal solution. Extensive computational experiments are performed on 96 generated scenarios. Two indicators were used to evaluate the Meta heuristics. The results indicate that Simulated Annealing and Genetic Algorithm presented better solutions for the given scheduling problem. Moreover considering the CPU time, Genetic Algorithm provided the solution in less time.

Abstract The goal of supply chain management is to enhance various functions of different parts and levels of a supply chain to obtain the maximum possible profit. But this goal is not completely achievable due to the fact that there are differences between mentioned parts and levels, in their attitude towards the goals. These differences, for example pricing, stocking, and the costs related to parts and levels, will gradually result in a deduction in strength and competitiveness in system. In this study, multi-echelon supply chain has been investigated using game theory approach and considering the dependence of demand to selling price, fuzzy marketing costs, and discounts for all units. The problem has been modeled assuming that there’s no cooperation between different levels. Also, Stackelberg model assumptions have been taken into account, in which each level, with respect to market conditions, can undertake the leadership task. The aim of this problem is to determine the best decision of each player to obtain the optimal order quantity, a shortage for manufacturer and the selling price of each player, and to maximize incomes, to minimize costs and in general, to maximize possible profit for all players participating in the chain. GAMS softwares and metaheuristic algorithms have been used to solve the problem. Finally, the profit for supply chain members’ in different leadership conditions have been analyzed by generating different examples.

Abstract In the world of constantly changing, there is no definitive and accurate information and Long-term decisions will have a significant impact on the future of the industry. Since no organization has unlimited resources, So the decision about the best strategy that makes organization closer to its goal is very important. Exist of Templates to select the best decisions in conditions of uncertainty help managers to make the future of their organization. This research aims at introducing and applying the theory of D-numbers as an extension of the Dempster-Shafer Theory, checking Decision-making and selection of appropriate and effective strategies at every point of the balanced scorecard in the electricity industry to cover uncertainty and incomplete information. To achieve this goal, the strategies were classified in each perspective, then Each perspective is examined separately. Dempster-Shafer theory in terms of the technical imperfections resolves a flaw information and by Considering the lack of information from human judgments it will give greater accuracy results.

Abstract Clustering techniques need to define the number of clusters before they can be applied to the partitioning problem. Determining suitable number of clusters in partitioning problem is the purpose of clustering validity indices, which are nowadays significantly considerable for data miners and this resulted in various numbers of related indices. Separation and compactness information of fuzzy clusters are both considered in developing the advance indices of clusters validity, while this makes the above mentioned indices inefficient because of mathematical sophistication and the need for more computational effort. Therefore, this paper proposes FCI as a new index, which employs fuzzy cardinality concept in defining the number of clusters in fuzzy clustering. FCI also considers both compactness and separation of fuzzy clusters while significantly decreases computational efforts. In this paper, after reviewing the cluster validity indices and fuzzy clustering algorithms, FCI index will be explained and ultimately to evaluate its effectiveness will be implemented.

Abstract Multi attribute decision making methods have an important role in solving real life problems. Decision making is difficult for managers due to the complexity of the problems and the uncertainty and vagueness of information. Interval-valued hesitant fuzzy set (IVHFS) is an effective tool to express uncertainty, vagueness and hesitancy. HFS and IVHFS are extensions of fuzzy set. In this paper, we develop the DEAMATEL-based analytic network process (DANP) method to solve the MADM problems with IVHFS information. Firstly, the deviation degree for interval-valued hesitant fuzzy elements (IVHFEs) is described and then the subtraction and division operations for IVHFEs is introduced. After which, for a better recognition of HFE or IVHFE, a new operator is proposed which simultaneously takes into account the score value and the deviation degree.  Next, the basics of DANP method are presented and after which, the principles and steps of the developed DANP method are introduced. Finally, the outsourcing of an airline company is verified by using the proposed method. Based on the result, the risk dimension is most important followed by compatibility, quality and cost. Also, flexibility in billing is the most important criterion.

Abstract Analysis decision-making patterns of buying behavior of customers and providing a predictive model is one of the challenges and areas of interest to researchers which can be widely used in the field of localization products. This study aimed to analyze and model the behavior of older customers decide to buy organic products with the hybrid approach. The research was done in two steps linked together. In the first step the reliability and validity of a questionnaire with 33 question was evaluated respectively by Cronbach's alpha and confirmatory factor analysis first and second order was approved. Opinion of 388 old customer using nine indicators were collected, then, using cluster analysis K-means based on Davies-Bouldin and sylvite criterion the optimal clusters was identified. And elderly clients in the two clusters were unwilling and eager to buy organic products was classified. In the second step purchasing behavior using decision tree models were analyzed and the optimum model was extracted "if-then" rules associated with each cluster were presented. The results showed that in both unwilling and eager cluster, education index predict the decisive factor in the decision to buy organic products, It also seems that the consumption of organic products among the elderly is not in good condition in this context proposals were presented for each cluster.

Abstract This study compares data mining techniques and fuzzy logic for Identify customer behavior and voice of the customer to be used in the process of target costing. In this research, the data relating to sales in the data warehouse of Farzad tile producing company in years 2014 and 2015 have been used. The results of the test of hypotheses suggest that the rate of correct prediction for customer features in neural-fuzzy networks with activation function, Fuzzy Clustering is 0.941and in Multi-layer Neural Network with sigmoid activation function is 0.927 and in the multi-layer neural network with tangent function is 0.882 and in Radial basis function network with Max softball function is 0.918. The results show that fuzzy neural network has better results than other methods used to predict the characteristics of the target customers.

Abstract In this study, a model is presented for fire station’s locating and facilities allocating to stations in different periods and emergency situations. This model is designed, considering amount of demands and facilities coverage radius, being dynamic (based on traffic and type of region) in different periods. According to fact, in the presented model, amount of demand for each demand point depends on number of coverage by facilities and amount of demand of demand point .in this model , location of stations is determined once in different periods. The numbers of facilities which are allocated to stations are allocated dynamically and can be relocated in different periods. In the model, each strategic demand point (arsenal, food storage and so on) can be potential point for facilities. This is a complicated model so to solve this model, particle swarm optimization algorithm and combinatorial matrix have been suggested. In the suggested algorithm, method of making matrix is such that locating matrix and early and final allocation are presented in a single matrix. Finally the results of proposed algorithm with artificial bee colony were compared the results show that this algorithm is better in terms of quality of answers and solving time.

Abstract In recent years offering after-sales services has been one of the most important factor in achieving customer satisfaction. Providing after-sales services and warranty implies an additional cost to the manufacturer. Therefore appropriate servicing strategy prevents unnecessary costs. Nowadays one of the common warranty Polices is outsourcing services to third-party warranty providers. An important issue that we are facing with is selecting the best provider. This article have developed MADM approach by using data mining for the selection of third-party warranty providers. This integrated approach includes clustering as a data mining tool and Step-wise Weight Assessment Ratio Analysis (SWARA) and VIKOR as the two MADM tools. After identifying the features that are important for outsourcing warranty from the perspective of the manufacturer, first third-party warranty service providers are clustered using data mining tools then VIKOR technique is used to rank the obtained clusters and the best cluster is selected. SWARA technique is used to weight decision criteria in VIKOR technique. Proposed approach was used in an electronic facilities company. Using data mining before the implementation of decision-making discovered the useful information that were hidden among historical data gathered by company and improved decision making process through providing effective information.

Abstract Decision-making is one of the main manager’s functions. Since different decision making approaches were emerged. Each of Philosophers, managers, sociologist and psychologists has different view to decision making. This research aim to have a new look at multiple criteria decision-making techniques by Pluralism theory. To achieve this goal we try to operationalize and redefine pluralism concept in the field of multiple criteria decision making. In this regard, Triangulation, Stability (sensitivity) analysis, Validity and Reliability as a quad dimension of pluralism is discussed. So the main innovation of present paper is extension of data pluralism beside of another three pillars of pluralism. Results of data pluralism reveal that there are significant relationship among Fuzzy, Crisp and grey approaches. Since the result of research is based of analyzing limited case, in Generalization of result, we must be cautious. Generalizability describes the extent to which research findings can be applied to settings other than that in which they were originally tested.Keywords: Quantative Decision Making, Pluralism, Triangulation, Reliability, Validity, Data Pluralism, Stability (Sensitivity).

Abstract Green supply chain management is consideredas an important organizational philosophy in the reduction of environmental hazards as well as a proactive approach to improve the environmental performanceand Achieve sustainable competitive advantages in organizations. The main aim of this study is to identify and measures the importance of a green supply chain management practices in the Field of Iran's Oil Industries. By reviewing the literature and using text content analysis approachwe recognizedfifteen green practices.The statistical population ofthis research included managers and experts familiar with the issue and working in the field of Iran's Oil Industries. Sample members were selected with targeted non-random sampling method.A researcher made questionnaire was used for data collection that its validity and reliability was confirmed. In order to achieve the purpose of research fuzzy mixed approachwas used. The results of analysis showed that legal requirements and regulations, and internal environmental management, design green, and green technology are the effecting practices in green supply chain management which require more emphasis and attention of managers on this kind of practices. It should be noted that the present study has innovation for development of theoretical concepts and the use of subjective judgment in determining the interal relations and using Fuzzy Integrated Approch.