Grey-Markov model of user demands prediction based on online reviews

Abstract

Users have higher demands on product with the developing e-commerce and the increasing online shopping. Enterprises must design products that meet user demands accurately and quickly to improve user satisfaction and increase product competitiveness. In the face of ever-changing user demands, enterprises need to predict the changing trend of user demands, so as to design products more in line with user demands and reduce the market risk of new product development. Therefore, this paper proposes a Grey-Markov model of user demands prediction based on online reviews for enterprises to predict the monthly changing trend of user demands in advance. Firstly, LDA topic model and sentiment analysis are used to get user attention values and user satisfaction values. Secondly, The Grey-Markov model of user demands prediction was established. According to two dimensions of the attention and satisfaction of user demands, the values of user demands are predicted, and the division of user demand improvement sequence is used to balance the scheme of product optimisation. Finally, taking the demand prediction and optimisation design of smartphones and automobiles for examples to illustrate the effectiveness of the proposed method and to provide a reference for manufacturing enterprises to optimise product design.

KEYWORDS:

• Online reviews
• Grey-Markov model
• demand prediction
• demand improvement sequence

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 Website of JingDong Mall is http://www.jd.com.

2 Website of PCauto is https://www.pcauto.com.cn.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China under Grant 72001203; the Fundamental Research Funds for the Central Universities under Grant 2020QN71; the Postgraduate Research & Practice Innovation Program of Jiangsu Province under Grant KYCX22_2676; the Graduate Innovation Program of China University of Mining and Technology under Grant 2022WLJCRCZL015.