Prediction of user's web-browsing behavior: Application of markov model

Mamoun A. Awad, Issa Khalil

Research output: Contribution to journalArticle

67 Citations (Scopus)

Abstract

Web prediction is a classification problem in which we attempt to predict the next set of Web pages that a user may visit based on the knowledge of the previously visited pages. Predicting user's behavior while serving the Internet can be applied effectively in various critical applications. Such application has traditional tradeoffs between modeling complexity and prediction accuracy. In this paper, we analyze and study Markov model and all- K th Markov model in Web prediction. We propose a new modified Markov model to alleviate the issue of scalability in the number of paths. In addition, we present a new two-tier prediction framework that creates an example classifier EC, based on the training examples and the generated classifiers. We show that such framework can improve the prediction time without compromising prediction accuracy. We have used standard benchmark data sets to analyze, compare, and demonstrate the effectiveness of our techniques using variations of Markov models and association rule mining. Our experiments show the effectiveness of our modified Markov model in reducing the number of paths without compromising accuracy. Additionally, the results support our analysis conclusions that accuracy improves with higher orders of all- K th model.

Original languageEnglish
Article number6163417
Pages (from-to)1131-1142
Number of pages12
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume42
Issue number4
DOIs
Publication statusPublished - 6 Mar 2012
Externally publishedYes

Fingerprint

Benchmarking
Internet
Classifiers
Association rules
Datasets
Scalability
Websites

Keywords

  • All-K th Markov
  • association rule mining (ARM)
  • Markov model
  • N-gram
  • two-tier architecture

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Human-Computer Interaction
  • Information Systems
  • Software

Cite this

Prediction of user's web-browsing behavior : Application of markov model. / Awad, Mamoun A.; Khalil, Issa.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 42, No. 4, 6163417, 06.03.2012, p. 1131-1142.

Research output: Contribution to journalArticle

@article{4248e094bd664138844f0ad75fe52da2,
title = "Prediction of user's web-browsing behavior: Application of markov model",
abstract = "Web prediction is a classification problem in which we attempt to predict the next set of Web pages that a user may visit based on the knowledge of the previously visited pages. Predicting user's behavior while serving the Internet can be applied effectively in various critical applications. Such application has traditional tradeoffs between modeling complexity and prediction accuracy. In this paper, we analyze and study Markov model and all- K th Markov model in Web prediction. We propose a new modified Markov model to alleviate the issue of scalability in the number of paths. In addition, we present a new two-tier prediction framework that creates an example classifier EC, based on the training examples and the generated classifiers. We show that such framework can improve the prediction time without compromising prediction accuracy. We have used standard benchmark data sets to analyze, compare, and demonstrate the effectiveness of our techniques using variations of Markov models and association rule mining. Our experiments show the effectiveness of our modified Markov model in reducing the number of paths without compromising accuracy. Additionally, the results support our analysis conclusions that accuracy improves with higher orders of all- K th model.",
keywords = "All-K th Markov, association rule mining (ARM), Markov model, N-gram, two-tier architecture",
author = "Awad, {Mamoun A.} and Issa Khalil",
year = "2012",
month = "3",
day = "6",
doi = "10.1109/TSMCB.2012.2187441",
language = "English",
volume = "42",
pages = "1131--1142",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Prediction of user's web-browsing behavior

T2 - Application of markov model

AU - Awad, Mamoun A.

AU - Khalil, Issa

PY - 2012/3/6

Y1 - 2012/3/6

N2 - Web prediction is a classification problem in which we attempt to predict the next set of Web pages that a user may visit based on the knowledge of the previously visited pages. Predicting user's behavior while serving the Internet can be applied effectively in various critical applications. Such application has traditional tradeoffs between modeling complexity and prediction accuracy. In this paper, we analyze and study Markov model and all- K th Markov model in Web prediction. We propose a new modified Markov model to alleviate the issue of scalability in the number of paths. In addition, we present a new two-tier prediction framework that creates an example classifier EC, based on the training examples and the generated classifiers. We show that such framework can improve the prediction time without compromising prediction accuracy. We have used standard benchmark data sets to analyze, compare, and demonstrate the effectiveness of our techniques using variations of Markov models and association rule mining. Our experiments show the effectiveness of our modified Markov model in reducing the number of paths without compromising accuracy. Additionally, the results support our analysis conclusions that accuracy improves with higher orders of all- K th model.

AB - Web prediction is a classification problem in which we attempt to predict the next set of Web pages that a user may visit based on the knowledge of the previously visited pages. Predicting user's behavior while serving the Internet can be applied effectively in various critical applications. Such application has traditional tradeoffs between modeling complexity and prediction accuracy. In this paper, we analyze and study Markov model and all- K th Markov model in Web prediction. We propose a new modified Markov model to alleviate the issue of scalability in the number of paths. In addition, we present a new two-tier prediction framework that creates an example classifier EC, based on the training examples and the generated classifiers. We show that such framework can improve the prediction time without compromising prediction accuracy. We have used standard benchmark data sets to analyze, compare, and demonstrate the effectiveness of our techniques using variations of Markov models and association rule mining. Our experiments show the effectiveness of our modified Markov model in reducing the number of paths without compromising accuracy. Additionally, the results support our analysis conclusions that accuracy improves with higher orders of all- K th model.

KW - All-K th Markov

KW - association rule mining (ARM)

KW - Markov model

KW - N-gram

KW - two-tier architecture

UR - http://www.scopus.com/inward/record.url?scp=84864147184&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864147184&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2012.2187441

DO - 10.1109/TSMCB.2012.2187441

M3 - Article

AN - SCOPUS:84864147184

VL - 42

SP - 1131

EP - 1142

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 4

M1 - 6163417

ER -