A New Estimation Method for Multivariate Markov Chain Model with Application in Demand Predictions

  • Authors:

  • Dong-Mei Zhu;Wai-Ki Ching

  • Affiliations:

  • -;-

  • Venue:
  • BIFE '10 Proceedings of the 2010 Third International Conference on Business Intelligence and Financial Engineering
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose a new estimation method for the parameters of a multivariate Markov chain model. In the new method, we calculate the correlations of the sequences first and establish multivariate Markov chain models for those positively correlated sequences. The parameters are estimated by minimizing the error of prediction. We apply the method to demand predictions for a soft-drink company in Hong Kong. Numerical experiments are given to show the effectiveness of our proposed method.