Research on duplicate combined forecasting method based on supply chain coordination

The coordinated forecast of agricultural means supply chain not only needs cooperation and information sharing among different parties but also needs scientific forecast methods and means. This paper firstly builds the synergetic framework of demand forecast and analyzes the key factors of demand fo...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing 2019-05, Vol.22 (Suppl 3), p.6621-6632
Main Authors: Zhu, Yanxin, Li, Sujian, Peng, Yongfang
Format: Article
Language:English
Subjects:
Access to information
Accuracy
Algorithms
Back propagation networks
Collaboration
Computer Communication Networks
Computer Science
Coordination
Demand
Forecasting
Information sharing
Information technology
Inventory
Mathematical analysis
Mathematical models
Methods
Neural networks
Operating Systems
Processor Architectures
Profits
Suppliers
Supply chain management
Supply chains
Time series
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The coordinated forecast of agricultural means supply chain not only needs cooperation and information sharing among different parties but also needs scientific forecast methods and means. This paper firstly builds the synergetic framework of demand forecast and analyzes the key factors of demand forecast coordination in different forecast stages and then confirms duplicate combined forecast method for time series based on the factors which influence the demand of agricultural means. GM(1,1) is used in the model to forecast the fluctuant items of long-term trend; BP neural network and ARMA are used to simulate periodically fluctuant items. Particle swarm algorithm is used to confirm the combined forecast model of periodically fluctuant items. Finally, a calculating example is used to compare the forecast precision of the combined forecast model, GM(1,1), BP neural network model and ARMA model. In conclusion, duplicate combined forecast model is applicable to forecasting the demand of agricultural means which are influenced by long-term trend and periodically fluctuant factors.
ISSN:1386-7857
1573-7543
DOI:10.1007/s10586-018-2356-z