Predictive collaborative performance system in B2B supply chain using neuro-fuzzy

Recently, contemporary B2B supply chain management (B2B-SCM) has been furnished with semi-automated data record systems to gather large quantities. Notwithstanding, most of companies and academic research groups have also concentrated on the results of the historical performance measurement interpre...

Full description

Saved in:
Bibliographic Details
Main Authors: Pongsak Holimchayachotikul, Komgrit Leksakul, Daniela Rita Montella, Matteo Savino
Format: Conference Proceeding
Published: 2018
Subjects:
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=79958762721&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/50781
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
Description
Summary:Recently, contemporary B2B supply chain management (B2B-SCM) has been furnished with semi-automated data record systems to gather large quantities. Notwithstanding, most of companies and academic research groups have also concentrated on the results of the historical performance measurement interpretation and relied on the things, what have already happened. These has been rarely concerned the performance inclination. It has resulted in the lack of well-rounded performance planning improvement in the long term. Moreover, they have focused on the physical operation performance enhancement without concerning the collaborative performance among their partners. On the grounds of the fact that, this paper is to present a Neuro-fuzzy system approach to construct collaborative performance which has forward looking collaborative capabilities and its linguistic rules to make understanding how to put the collaborative performance directions in another time. The methodology is as follows. Firstly, B2B-SC performance evaluation questionnaires, with two levels were able to distinguish collaborative relation between two or more partners in their SC were congregated from the case study chains. The data set of relationships between enterprise and its direct clients of the case study companies in France was used for manifestation. Secondly, data cleaning and preparations before the proposed model construction. The multi attribute decision making, simple additive weighting, was employed to build the collaborative performance scoring model, as well. Thirdly, the pervious results were us e as the learning dataset to make up of the predictive collaborative performance system based on Neuro-fuzzy. Finally, the result deployment for collaborative performance guideline from model was validated by the domain experts in term of its real practical usage efficiency. The developed system enables managers to develop systematic manners to foresee future collaborative performance and recognize latent problems in their collaboration. The prognostic ability of the developed system is comparable with the decision of the manager in their collaboration. The comment on its usages and difficulties in its developed process are also discussed. Furthermore, the final predictive results and rules contain very interesting information relating to SC improvement in long runs.