Font Size: a A A

Study On Regional Logistics Demand Forecasting Based On PCA-SVR

Posted on:2019-02-08Degree:MasterType:Thesis
Country:ChinaCandidate:L Y BaoFull Text:PDF
GTID:2429330548978874Subject:Logistics Engineering
Abstract/Summary:PDF Full Text Request
Logistics is closely related to the development of economy.With the rapid growth of the global economy,the impact of logistics on the economy is more significant.In the long run,the upgrading of regional logistics plays a very important role in promoting regional economic growth.The regional logistics demand is the premise and basis for the development of logistics development strategies in the region,and is an important basis for the overall planning of the functional positioning and spatial distribution of regional logistics.By forecasting the regional logistics demand,it will help better play the regional competitive advantage and promote the sound and rapid development of the regional economy and logistics industry.Based on the relationship between regional logistics development and regional economy,this paper establishes a set of indicators for forecasting regional logistics demand based on the factors that influence regional logistics demand and the basic principles of index system construction.Then,the correlation degree of the index system is calculated by the grey correlation analysis method,and the index system for regional logistics demand forecast in Anhui Province is selected.Secondly,this paper analyzes the current research status at home and abroad from the aspects of regional logistics influencing factors and logistics demand forecasting methods,and then chooses Radial Basis Function(RBF)neural network and Support Vector Machine(SVR)model as prediction models.In order to improve the accuracy of demand forecasting,principal component analysis(PCA)is used to reduce the dimension of data,and a support vector regression(PCA-SVR)prediction model based on principal component analysis is established.Finally,this paper takes Anhui Province as an example,uses PCA-SVR model to forecast the regional logistics demand in Anhui Province,and compares the prediction results to verify the validity of the model.And using the grey prediction and PCA-SVR model to predict the regional logistics demand in Anhui Province in 2018,the results show that the freight turnover of Anhui Province in 2018 was 1,256,298 million ton kilometers,indicating that the logistics demand in Anhui Province is still increasing.At the same time,the policy suggestions are provided for the future development of the logistics industry in Anhui province from three levels.
Keywords/Search Tags:Regional logistics, Logistics demand, Principal component analysis, RBF neural network, PCA-SVR
PDF Full Text Request
Related items