International Journal of Computational Intelligence Systems

Volume 13, Issue 1, 2020, Pages 1253 - 1264

Discovering Potential Partners via Projection-Based Link Prediction in the Supply Chain Network

Authors
Zhi-Gang Lu*, ORCID, Qian Chen
Department of Management Science, Shanghai Maritime University, 1550 Haigang Road, Pudong New District, Shanghai, China
*Corresponding author. Email: zglu@shmtu.edu.cn
Corresponding Author
Zhi-Gang Lu
Received 29 August 2019, Accepted 7 August 2020, Available Online 21 August 2020.
DOI
10.2991/ijcis.d.200813.001How to use a DOI?
Keywords
Supply chain network; Resilience; Potential partners; Link prediction
Abstract

As reserving a certain number of potential partners plays a significant role in alleviating existing partners' collaborative interruption risks, we investigate the process of discovering potential partners to improve the supply chain network's resilience. Most of the existing research confines its focus on discovering potential partners in the supply chain on the basic of sufficient partners' information, but very few works consider discovering potential partners in the supply chain network according to the structure of the supply chain network when the partner information is insufficient. In this situation, a novel model which applies projection-based link prediction method to discover potential partners in the supply chain network is proposed. The proposed model is composed of three stages. The first stage is predicting the candidate partnerships links based on the projection one-model graph which is transformed from the supply chain network according to its structure. The second stage is discovering potential partners by comparing the acquired connectivity of candidate partnership links with the maximal connectivity of existent partnerships. In the third stage, a resilience evaluation framework considering the both connectivity and flexibility indexes is presented to determine whether the supply chain network's agility is improved. In the experimental design, a supply chain network which is formed from a real dataset containing mobile phone suppliers, manufacturers and packers is used to evaluate the proposed algorithm's prediction accuracy. The results reveal that the algorithm achieves highest area under curve (AUC) scores and the supply chain network's resilience is improved by discovering potential partners.

Copyright
© 2020 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
13 - 1
Pages
1253 - 1264
Publication Date
2020/08/21
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
10.2991/ijcis.d.200813.001How to use a DOI?
Copyright
© 2020 The Authors. Published by Atlantis Press B.V.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - JOUR
AU  - Zhi-Gang Lu
AU  - Qian Chen
PY  - 2020
DA  - 2020/08/21
TI  - Discovering Potential Partners via Projection-Based Link Prediction in the Supply Chain Network
JO  - International Journal of Computational Intelligence Systems
SP  - 1253
EP  - 1264
VL  - 13
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.200813.001
DO  - 10.2991/ijcis.d.200813.001
ID  - Lu2020
ER  -