Higher-order multivariate Markov chains and their applications. (English) Zbl 1144.65006

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

Linear Algebra Appl. 428, No. 2-3, 492-507 (2008).

High order multivariate Markov chains are frequently used in modelling, especially for the catagorical data sequences. To reduce the number of the estimated parameters, in some stationary cases, the authors provide a conditional minimum-maximum algorithm associated with the frequency estimation to identify the modelling parameters to meet the practical use. An application to sales demand prediction is discussed.

Reviewer: Gong Guanglu (Beijing)

MSC:

65C40	Numerical analysis or methods applied to Markov chains
60J22	Computational methods in Markov chains

Keywords:

Perron-Frobenius theorem; multivariate Markov chains; categorical data sequences; conditional minimum-maximum; sales demand prediction

References:

[1]	Buzacott, J.; Shanthikumar, J., Stochastic Models of Manufacturing Systems (1993), Prentice-Hall: Prentice-Hall New Jersey · Zbl 1094.90518
[2]	Ching, W., Iterative Methods for Queuing and Manufacturing Systems (2001), Springer: Springer London · Zbl 0976.60086
[3]	Ching, W.; Fung, E.; Ng, M., A multivariate Markov chain model for categorical data sequences and its applications in demand predictions, IMA J. Manage. Math., 13, 87-199 (2002) · Zbl 1040.62108
[4]	Ching, W.; Fung, E.; Ng, M., A higher-order Markov model for the newsboy’s problem, J. Operat. Res. Soc., 54, 291-298 (2003) · Zbl 1171.90539
[5]	Ching, W.; Fung, E.; Ng, M., Higher-order Markov chain models for categorical data sequences, Int. J. Nav. Res. Logist., 51, 557-574 (2004) · Zbl 1054.62098
[6]	Ching, W.; Ng, M., Advances in Data Mining and Modeling (2003), World Scientific: World Scientific Singapore
[7]	Ching, W.; Yuen, W.; Loh, A., An inventory model with returns and lateral transshipments, J. Operat. Res. Soc., 54, 636-641 (2003) · Zbl 1095.90503
[8]	Ching, W.; Fung, E.; Ng, M.; Akutsu, T., On construction of stochastic genetic networks based on gene expression sequences, Int. J. Neural Syst., 15, 297-310 (2005)
[9]	Chvátal, V., Linear Programming (1983), Freeman: Freeman New York · Zbl 0318.05002
[10]	Fang, S.; Puthenpura, S., Linear Optimization and Extension (1993), Prentice-Hall: Prentice-Hall London
[11]	Fleischmann, M., Quantitative Models for Reverse, Logistics. Quantitative Models for Reverse, Logistics, Lecture Notes in Economics and Mathematical System, vol. 501 (2001), Springer: Springer Berlin · Zbl 0966.90037
[12]	Horn, R.; Johnson, C., Matrix Analysis (1985), Cambridge University Press: Cambridge University Press Cambridge, UK · Zbl 0576.15001
[13]	MacDonald, I.; Zucchini, W., Hidden Markov and Other Models for Discrete-valued Time Series (1997), Chapman & Hall: Chapman & Hall London · Zbl 0868.60036
[14]	Nahmias, S., Production and Operation Analysis (1997), McGraw Hill International: McGraw Hill International Chicago
[15]	Raftery, A., A model for high-order Markov chains, J.R. Statist. Soc. B, 47, 528-539 (1985) · Zbl 0593.62091
[16]	Sharma, O., Markovian Queues (1995), Ellis Horwood: Ellis Horwood New York · Zbl 0743.60103
[17]	Siu, T.; Ching, W.; Ng, M.; Fung, E., On multivariate credibility approach for portfolio credit risk measurement, Quantitative Finance, 5, 543-556 (2005) · Zbl 1134.91485