Design of an integrated knowledge management system for component distributors in China

Pao Yue-kong Library Electronic Theses Database

Design of an integrated knowledge management system for component distributors in China


Author: Chow, Yiu-cheong
Title: Design of an integrated knowledge management system for component distributors in China
Degree: M.Sc.
Year: 2005
Subject: Hong Kong Polytechnic University -- Dissertations
Knowledge management
Business logistics
Stores and stock-room keeping -- Automation
Physical distribution of goods
Neural networks (Computer science)
Department: Dept. of Industrial and Systems Engineering
Pages: xii, 139 leaves : ill. ; 30 cm
Language: English
InnoPac Record:
Abstract: The electronic spare parts market has been growing internationally. Most distributors understand that the service parts logistics is critical to customer satisfaction and competitivenes. They realize that the market in China has the potential to profit their business. One strategy to do that is the redesign of its stock availability for service parts supply chain network. Typical component distribution has much larger, higher value inventories with fewer stock turns than conventional distribution operations. This is because a large number of stock keeping units (SKU) must be available to meet the urgent requirements such as emergency repair or production. Unlike conventional distribution where the 80:20 rule often applies, 80% of the throughput is generated by 20% of the product range, the relationship in many component distribution is more likely to be around 90:10, which means that only a very small number of SKUs are responsible for a very high percentage of order throughput. Thus, capturing transaction data and transferring as knowledge become the key success factor to component distributors. In order to satisfy the requirement, a knowledge management system must be designed to understand their need & preference. It relies heavily on how to capture information and experience effectively. Reviewing of publications indicates that whilst many research activities are done only on data collection whilst many research activities are done on data warehouse, OLAP system and Neural Network. The research in the area relates to the seamless integration among data collection, the drill down process and recommendation have not received the attention it deserves. This issue is addressed in this research with the introduction of an integrated system by integrating data warehouse, OLAP, system, and neural network, providing a synergetic combination of various techniques and technologies related to knowledge discovery. This report presents an Integrated Knowledge Management System (IKMS) that Viable System Model acts as the high level reference architecture. The function of IKMS is to facilitate the collection, recording, organization, filtering, analysis, retrieval, and dissemination of explicit knowledge. This explicit knowledge consists of all documents, accounting records, and data stored in computer memories. In order to gain the competitive advantage, this system performs an explicitly strategic function for component distributors in a fast changing business environment. By integrating with On-line Analytical Processing (OLAP) and Artificial Neural Network (ANN) technologies, OLAP helps customers to analyze with a large database or a data warehouse to gain insight on the information it contain with the framework of data mining rapidly. ANN modelling transfers information to knowledge that adds value to the business activites of decision support and application with different input module. The methodology helps understanding the market segmentation, customer ranking and sales & inventory forecasting. With applying the above technologies, an IKMS predicts the customer trend and pattern with a high accuracy so that an effective functional strategy can be recommended for enhancing the competitive advantage of spare parts & component distributors. This project studies past data from the record of customers and advises an inventory strategy to component distributors. The result illustrates a high accurate forecasting with a detailes evaluation of the neural network solution and verification by the simulation. Using the method proposed in this project, and Ad hot list is developed for the stock auto-replenishment. The total inventory turn of the component distributor had been improved from 3 to 8.31. The recommended inventory strategy helps the component distributor keeping the right electronics spare parts at the right place with a high service level standard.

Files in this item

Files Size Format
b18099877.pdf 12.33Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.


Quick Search


More Information