Title: Big data prediction method of traffic logistics demands based on regional differences

Authors: Rongting Sun; Yiqun Guo

Addresses: School of Economics and Management, Chang'an University, Xi'an 710064, Shaanxi, China ' Xi'an Physical Education University, Xi'an 710068, Shaanxi, China

Abstract: Aiming at the optimisation effect of traditional methods on logistics transportation, and the inaccurate prediction of logistics demand, this paper proposes a big data forecasting method for traffic logistics demand based on regional differences. Based on the regional differences, a linear statistical programming model for the prior data of traffic logistics demand data is established. On this basis, the association rule feature decomposition and average mutual information analysis are carried out for the traffic logistics demand big data. The BP fuzzy decision classification model is adopted for feature information clustering and information fusion processing of traffic logistics demand big data to optimise the big data prediction model. The simulation results show that the model has higher accuracy and better global convergence in the big data forecast of traffic logistics demand, which improves the overall forecasting ability, and the forecasting time is reduced by 12.8% compared with the traditional method.

Keywords: regional difference; traffic logistics; big data prediction; fuzzy decision; linear planning model.

DOI: 10.1504/IJITM.2021.10037419

International Journal of Information Technology and Management, 2021 Vol.20 No.3, pp.221 - 233

Received: 23 Feb 2019
Accepted: 29 May 2019

Published online: 28 Apr 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article