A novel discrete grey multivariable model and its application in forecasting the output value of China's high-tech industries. (January 2019)

• Record Type: Journal Article
• Authors: Ding, Song
• Is Part Of: Computers & industrial engineering. Volume 127(2019)
• Page Start: 749
• Page End: 760
• Publication Date: 2019-01
• Subjects: Grey prediction model -- Accumulative effects -- Ant lion optimizer -- High-tech industries -- Output-value forecast; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2018.11.016
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: A grey model is designed for forecasting the output value of China's eastern high-tech industries. The novel grey model considers the accumulative effects of R&D investments and personnel. The Ant Lion Optimizer is employed to determine the generating parameters. The proposed model outperforms the competing models in the empirical study. The future output values are predicted from 2016 to 2020. Abstract: An improved discrete grey multivariable model is designed to forecast the future output value of the high-tech industries that cover large and medium-sized enterprises (LMEs) in China's eastern region. Although the high-tech industries have become a major concern due to their great economic worth, few studies have been carried out to consider the accumulative effects of research and development (R&D) inputs on the output-value growth. Therefore, to address such a challenge problem, three critical contributions are provided in this paper: first, an accumulative discrete grey multivariable model is built that considers the accumulative effects of R&D inputs on the output-value growth; second, the Ant Lion Optimizer (ALO), an intelligent algorithm, is employed to determine the optimal accumulative coefficients; third, an one-step rolling mechanism, which takes into account the most recent data for model calibration, is utilized to further enhance the forecasting capability. To verify the efficacy and practicality of this proposed model, data sets from the eastern high-tech industries (2007–2015) are employed in the forecasting experiments. The empirical results demonstrate that the proposed model outperforms a range of benchmark models. Therefore, this superior model is employed for forecasting future output value of the eastern high-tech industries from 2016 to 2020. Based on the empirical findings, some suggestions are presented to further promote the development of China's high-tech industries.