Higher-order Markov chain models for categorical data sequences

Wai Ki Ching; Eric S. Fung; Michael K. Ng

doi:10.1002/nav.20017

Higher-order Markov chain models for categorical data sequences

Wai Ki Ching
, Eric S. Fung
, Michael K. Ng^*

^*Corresponding author for this work

Department of Mathematics

Research output: Contribution to journal › Journal article › peer-review

75 Citations (Scopus)

Abstract

In this paper we study higher-order Markov chain models for analyzing categorical data sequences. We propose an efficient estimation method for the model parameters. Data sequences such as DNA and sales demand are used to illustrate the predicting power of our proposed models. In particular, we apply the developed higher-order Markov chain model to the server logs data. The objective here is to model the users' behavior in accessing information and to predict their behavior in the future. Our tests are based on a realistic web log and our model shows an improvement in prediction.

Original language	English
Pages (from-to)	557-574
Number of pages	18
Journal	Naval Research Logistics
Volume	51
Issue number	4
Early online date	15 Mar 2004
DOIs	https://doi.org/10.1002/nav.20017
Publication status	Published - Jun 2004

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

User-Defined Keywords

Categorical data
Higher-order Markov model
Linear programming

Access to Document

10.1002/nav.20017

Cite this

@article{b164db19812e488d9b5cf7f99af51a7f,

title = "Higher-order Markov chain models for categorical data sequences",

abstract = "In this paper we study higher-order Markov chain models for analyzing categorical data sequences. We propose an efficient estimation method for the model parameters. Data sequences such as DNA and sales demand are used to illustrate the predicting power of our proposed models. In particular, we apply the developed higher-order Markov chain model to the server logs data. The objective here is to model the users' behavior in accessing information and to predict their behavior in the future. Our tests are based on a realistic web log and our model shows an improvement in prediction.",

keywords = "Categorical data, Higher-order Markov model, Linear programming",

author = "Ching, \{Wai Ki\} and Fung, \{Eric S.\} and Ng, \{Michael K.\}",

note = "The research of this project is supported by RGC Grant Nos. HKU 7130/02P, HKU 7126/02P, and 7046/03P and HKU CRCG Grant Nos. 10203501, 10203907, 10204436, and 10204437 Publisher Copyright: {\textcopyright} 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004",

year = "2004",

month = jun,

doi = "10.1002/nav.20017",

language = "English",

volume = "51",

pages = "557--574",

journal = "Naval Research Logistics",

issn = "0894-069X",

publisher = "John Wiley \& Sons Ltd",

number = "4",

}

TY - JOUR

T1 - Higher-order Markov chain models for categorical data sequences

AU - Ching, Wai Ki

AU - Fung, Eric S.

AU - Ng, Michael K.

N1 - The research of this project is supported by RGC Grant Nos. HKU 7130/02P, HKU 7126/02P, and 7046/03P and HKU CRCG Grant Nos. 10203501, 10203907, 10204436, and 10204437 Publisher Copyright: © 2004 Wiley Periodicals, Inc. Naval Research Logistics, 2004

PY - 2004/6

Y1 - 2004/6

N2 - In this paper we study higher-order Markov chain models for analyzing categorical data sequences. We propose an efficient estimation method for the model parameters. Data sequences such as DNA and sales demand are used to illustrate the predicting power of our proposed models. In particular, we apply the developed higher-order Markov chain model to the server logs data. The objective here is to model the users' behavior in accessing information and to predict their behavior in the future. Our tests are based on a realistic web log and our model shows an improvement in prediction.

AB - In this paper we study higher-order Markov chain models for analyzing categorical data sequences. We propose an efficient estimation method for the model parameters. Data sequences such as DNA and sales demand are used to illustrate the predicting power of our proposed models. In particular, we apply the developed higher-order Markov chain model to the server logs data. The objective here is to model the users' behavior in accessing information and to predict their behavior in the future. Our tests are based on a realistic web log and our model shows an improvement in prediction.

KW - Categorical data

KW - Higher-order Markov model

KW - Linear programming

UR - https://www.scopus.com/pages/publications/2342466776

UR - https://onlinelibrary.wiley.com/doi/10.1002/nav.20017

U2 - 10.1002/nav.20017

DO - 10.1002/nav.20017

M3 - Journal article

AN - SCOPUS:2342466776

SN - 0894-069X

VL - 51

SP - 557

EP - 574

JO - Naval Research Logistics

JF - Naval Research Logistics

IS - 4

ER -

Higher-order Markov chain models for categorical data sequences

Abstract

UN SDGs

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this