Please use this identifier to cite or link to this item:
Title: A knowledge- based system to support procurement decision
Authors: Lau, HCW
Ning, A
Pun, KF
Chin, KS
Ip, WH  
Keywords: Deductive databases
Decision support systems
Issue Date: 2005
Publisher: Emerald Group Publishing Limited
Source: Journal of knowledge management, 2005, v. 9, no. 1, p. 87-100 How to cite?
Journal: Journal of knowledge management 
Abstract: Purpose – To propose an infrastructure of a knowledge‐based system to capture and maintain the procurement information and purchasers' knowledge, regarding how to choose partners in the supply chain network, with the adopting of the neural networks that mimic the operation of human brain to generate solution systematically.
Design/methodology/approach– The proposed system encompasses hybrid artificial intelligence (AI) technologies, Online analytical processing (OLAP) applications and neural networks.
Findings– Be able to capture the procurement data and vendors' information that are generated in the workflows to ensure tthat he knowledge and structured information are captured without additional time and effort. Recognizes the void of research in the infrastructure of the hybrid AI technologies for knowledge discovery.
Research limitations/implications– Neural network does not have the sensibility characteristic of the purchasing staff, it is not able to identify the environment changes, which need to re‐adjust the output to fit the environment. Practical implications – The proposed system obtains useful information related to the trend of sales demand in terms of customer preference and expected requirement using the OLAP module and then based on this information, the neural network provides recommendation related to the supported suppliers that are capable of fulfilling the requirements.
Originality/value– This paper proposes a knowledge‐based system that offers expandability and flexibility to allow users to add more related factors for analysis to enhance the quality of decision making.
ISSN: 1367-3270
EISSN: 1758-7484
DOI: 10.1108/13673270510582983
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Nov 13, 2018

Page view(s)

Last Week
Last month
Citations as of Nov 11, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.