Please use this identifier to cite or link to this item:
Title: Web profiling and navigation path analysis
Authors: Lam, Ming Yan (林洺因)
Department: Department of Computer Science
Issue Date: 2006
Course: CS4512
Programme: BSCS/BSCCS
Supervisor: Dr. Wong, Hau San. First Reader: Dr. Ngo, Chong Wah. Second Reader: Dr. Kwong, Sam
Subjects: Web site development
Web site design
Data mining
Description: Nominated as OAPS (Outstanding Academic Papers by Students) paper by Department in 2006-07.
Abstract: The rich information in the World Wide Web has created an information overloading problem for web users. The technology of Web personalization targets to solve such a problem and thus recommendation systems were studied. Nowadays, Web Usage Mining technique is overtaking the position of traditional collaborative filtering technology, moving traditional ranking style into web log and navigation path analysis approach. The Markov model is one of the well performed prediction model that is suitable for a recommendation system. However, it suffers from state complexity problem and needs to be improved. Association Rule mining is another technique for data mining and pattern discovery. There is also room to improve for the performance of Association Rule. This project focuses on the studies of different optimization schemes for Markov model and Association Rule. It takes experiments on different kinds of improvement studies. It also shows the result of different kinds of model optimization scheme. A profiling modeler and an online recommendation engine are also implemented for testing and simulation.
Appears in Collections:Computer Science - Undergraduate Final Year Projects
OAPS - Dept. of Computer Science

Files in This Item:
File SizeFormat 
fulltext.html162 BHTMLView/Open

Items in Digital CityU Collections are protected by copyright, with all rights reserved, unless otherwise indicated.