Forecasting the economic indices of the high-tech industries in China using the grey multivariable convolution model

Abstract

Reliable output forecasts are critical for decision-making and planning in high-tech industries. Several endogenous and exogenous factors could influence the output dynamics, and thereby a univariate model that only incorporates historical data and single method improvement is typically insufficient to generate accurate projections. In this paper, a novel grey multivariable convolution model is designed from a collaborative optimization perspective. The core innovations of this study can be summarized as follows. Initially, a collaborative framework integrating background value optimization, data preprocessing, and model structure improvement is constructed, which overcomes the internal deficiencies of the conventional grey models. Secondly, the Particle Swarm Optimization algorithm is selected to determine the optimal values of the damping accumulation parameters to enhance the adaptability and flexibility of the proposed model. Further, for validation purposes, experiments on forecasting the output of high-tech industries considering R&D investments are conducted from the national and provincial levels, among which six competing models are involved. Moreover, Monte-Carlo Simulation, incorporated with probability density analysis and statistical analysis, is introduced to evaluate the robustness of the newly-designed model. It can be demonstrated from the empirical results that the novel model is a reliable and promising method for predicting the economic indices of the high-tech industries with enhanced forecasting capability.