Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/83294
Title: A knowledge-based decision support system for managing logistics operations under risk considerations
Authors: Lam, Hoi Yan
Degree: Ph.D.
Issue Date: 2014
Abstract: In order to survive in today's highly competitive business environment, the function of the warehouse in a supply chain is no longer only to keep a large amount of stock in storage. Instead, customer orders with high product varieties in small quantities are often received by the logistics service providers (LSPs), with requests for customized value-added services and timely delivery. However, each type of stock keeping unit needs different handling methods due to its specific characteristics, which increases the pressure on LSPs and forces them to change their strategic goals for achieving shorter order cycle times, lower costs, and better customer service. Therefore, the fulfillment of customer orders in the warehouse becomes challenging in order to satisfy increasing customer demand in terms of responsiveness, cost effectiveness and flexibility. In addition, due to the uncertainty and rapid changes in the business environment, the performance of warehouse operations is not only affected by the logistics strategy planning process, but also the possible risks that may occur during the logistics operations. Since the decision making process is one of the complicated processes involved in warehouse operation, attention should be paid to establishing a knowledge-based decision support system to support the planning of responsive logistics strategies that can be formulated to fulfill the demand of high efficiency and quality in logistics service requirements.
In order to facilitate the decision making process in warehouse operations, an intelligent system, namely the Knowledge-based Logistics Operations Planning System (K-LOPS) is proposed to formulate a useful action plan by considering the potential risks faced by the LSPs. The proposed system consists of three modules: real-time data collection module (RDCM), warehouse risk assessment module (WRAM), and, logistics strategy formulation module (LSFM). RDCM collects real time logistics data, which enables instant monitoring of the inventory and resources status in the warehouse. WRAM provides a systematic approach in categorizing the potential risk factors considered by customers based on the different product characteristics, and is an important step to meet customer expectation. LSFM formulates the logistics operations strategy including critical operation procedures, useful guidelines and workflow to deal with the potential risks faced when fulfilling customer orders. Since the operational mechanism of LSFM relies on past explicit knowledge in order to provide references in formulating new solutions, a newly-designed algorithm, namely iterative dynamic partitional clustering (iDPC) algorithm, is integrated into the search engine to improve the performance in retrieving accurate and useful past similar cases. To validate the feasibility of the proposed system, two cases studies have been conducted in a third party logistics company and a wine distribution hub, both of which are based in Hong Kong. Through the pilot run of the system in the two case studies, improvement of follow-up action formulation and warehouse operation effectiveness was observed. Meanwhile, a generic methodology related to the design and implementation of the proposed system is described, which provides a roadmap for the logistics service providers to follow. The major contribution of this research is in the design and implementation of an effective system, which facilitates appropriate decision making in providing diverse logistics strategy formulation, by emerging real-time data capturing technology and hybrid artificial intelligent techniques for risk assessment and decision making in the logistics industry.
Subjects: Business logistics -- Data processing.
Business logistics -- Decision making.
Business logistics -- Risk management.
Hong Kong Polytechnic University -- Dissertations
Pages: xiv, 210 p. : ill. (some col.) ; 30 cm.
Appears in Collections:Thesis

Show full item record

Page views

73
Last Week
0
Last month
Citations as of Mar 24, 2024

Google ScholarTM

Check


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