Research Of Retail Terminal Location In Supply Chain Network Of X Company

With the rapid development of economy,the development of China's tobacco industry is facing the double pressures at home and abroad.In this context,diversification has become the trend of tobacco enterprise development.How to choose high-quality non tobacco retail terminal is the urgent need to solve the problem of tobacco companies.Supply chain network retail terminal location is the most important part of enterprise management terminal,The quality of the site has an important direct impact on the service mode,service quality,service efficiency and service level of the enterprise,which indirectly affects the efficiency and competitiveness of the enterprise.This paper takes X companies as an example to study the problem of non tobacco products supply chain network retail terminal location,and puts forward the solution to the problem.Firstly,the evaluation index system of the terminal location of non tobacco products supply chain network is constructed.In order to solve the problem of redundancy and reduce the computational complexity,the attribute reduction in rough set theory is used to simplify the index system.In this paper,the 4 factors,such as the population factor,the trade area factor,the traffic factor and the network factor,are used as the evaluation index system of the level of population density,the income level of the population,the number of public transportation,and so on,which are the 14 indexes of the two levels.Secondly,the weight of the evaluation index system is solved by using entropy weight method and variable weight method.According to the survey and enterprise system data,30 sites were selected as the research object,and the entropy weight method was used to determine the weight of the index system.In order to solve the problem of "state imbalance" caused by the change of the influence of each factor,the author puts forward the idea of variable right and the vector of dynamic adjustment to make the evaluation result more accurate.Thirdly,the location decision model based on entropy weight and support vector machine is proposed.The entropy weight-SVM regression prediction model is constructed by using the weight of the entropy weight and the variable weight as the sample set of the support vector machine,and the site selection scheme is selected according to the predicted sales of the alternative network.Finally,the model is analyzed empirically and Put forward the location decision of X company.The data of 15 non tobacco sales outlets are selected,and the other is the training sample set of entropy weight-SVM,and the 5 is the test sample set of entropy weight-SVM,in which the influence factors are set as input variables,and the output of is the output variable.The use of Libsvm software to achieve sales forecast,and Rank them,X company should choose the higher ranking network and establish the partnership from the existing alternative outlets...