Research on Regional Logistics Demand Forecast Based on Improved Support Vector Machine: A Case Study of Qingdao City under the New Free Trade Zone Strategy

Nan Yu,Wei Xu,Kai-Li Yu

doi:10.1109/access.2019.2963540

Abstract

Based on the analysis on the influencing factors of urban logistics demand, this paper, taking into account the logistics demand with non-linear and small sample modeling characteristics from the perspective of urban freight volume, introduces the ant colony algorithm into the modeling process to optimize the penalty parameter “c” and “g” parameter of Radial Basis Function in support vector machine, and has made a prediction to the logistics demand of Qingdao with the optimized support vector machine model. The experimental results show that the prediction results of the improved support vector machine can bring the prediction closer to the reality with their more accuracy, stronger stability and less error rate, thus providing a guarantee for the logistics demand forecast of Qingdao.

Highlights

Urban logistics demand forecasting is based on the analysis of relationship between supply and demand of logistics
Yu et al.: Research on Regional Logistics Demand Forecast Based on Improved Support Vector Machines (SVM): Case Study of Qingdao City impact of urban logistics development on economic growth
For the sample data sets that is inseparable and very difficult the ACO-SVM model improves the classification accuracy more obviously

Summary

INTRODUCTION

Urban logistics demand forecasting is based on the analysis of relationship between supply and demand of logistics. In order to obtain the optimal parameters of the second-order gray prediction model, the paper uses the neural network mapping method to establish a second-order gray neural network prediction model It shows that the proposed method can effectively improve the accuracy of load prediction. The support vector machine algorithm is applied to the the forecasting research of urban logistics demand by detecting the classification accuracy of four different kernel functions, the RBF kernel function with the highest classification accuracy is found, and the c and g parameters affecting the prediction accuracy of support vector machine are optimized by ant colony algorithm to establish improved the prediction model of support vector machine. It can consider the influence of other factors on the prediction object, and has the advantage of improving the prediction accuracy degree, in the prediction result, people can get more reliable and accurate results that support Qingdao’s logistics development in data aspect

INDEX SYSTEM CONSTRUCTION OF URBAN LOGISTICS DEMAND FORECASTING

Findings

DATA ACQUISITION AND PREPROCESSING