Table of Content

01 March 2023, Volume 35 Issue 1

Previous Issue    Next Issue

An Improved Grey Time-Delay Multivariable Model and Its Application

Huimin Zhou, Haifeng Lin, Junjie Wang, Yaoguo Dang, Yingjie Yang, Yu Feng

2023, 35(1):  1-19. 

Asbtract ( 36 )  

Related Articles | Metrics

An accurate output value prediction is of great significance for policy-making and plan development in high-tech industries. An adaptive cumulative time-delay discrete grey multivariable model is proposed to forecast the output value of hightech industries in China. Specifically, a new time-delay function is constructed to unify the time-delay effects and facilitate a realistic adaptation to disparate timedelay effects. Subsequently, the Grey Wolf Optimizer algorithm is used to find the optimal parameters for the new time-delay function, which improves the model’s adaptability. Furthermore, to further enhance the model’s prediction accuracy, an iterative reweighted least squares method is also adopted to optimize the parameter vector. To demonstrate the applicability of the proposed model, it is employed in hightech industries in China. The empirical findings show that the proposed model outperforms the benchmark models. 

Forecasting Seasonal Changes in Ocean Acidification Using a Novel Grey Seasonal Model with Grey Wolf Optimization

Kedong Yin, Kai Zhang, Wendong Yang

2023, 35(1):  20-38. 

Asbtract ( 43 )  

Related Articles | Metrics

Ocean acidification forecasting has important implications for studying global carbon dioxide emissions reductions. However, due to seasonal and cyclical features, ocean acidification forecasting remains an extremely challenging task. Therefore, this paper proposes a grey wolf optimized fractional-order-accumulation discrete grey seasonal model (GFSM(1,1)). The GFSM(1,1) model improves the prediction of ocean acidification in two ways: The new information priority of seasonal data is improved by the fractional accumulation operator, and the adaptability of the grey model to seasonal data is increased by seasonal item parameters. The above two works have significantly improved the prediction accuracy of the grey prediction model for ocean acidification. The prediction results in practical cases prove that the prediction effect of the GFSM(1,1) model is not only better than the existing grey models (FMGM(1,N)、NSGM(1,N), and GM(1,1)) but also better than statistical models (Nonlinear regression and ARIMA), traditional neural network model (LSTM) and deep learning model (SVM). Finally, the GFSM(1,1) model is applied to the prediction of seawater acidification. The forecast results show that the ocean will be acidified at a rate of 0.001863 per year, and the pH of the ocean will decrease by about 0.03% per year compared to the same period in previous years. 

A Novel Negative Grey Relation Model for Reverse Sequences

Ningning Lu, Sifeng Liu, Junliang Du, Ding Chen, Xiaochao Qian

2023, 35(1):  39-48. 

Asbtract ( 45 )  

Related Articles | Metrics

Grey relation analysis model is used to analyze the degree to which a factor affects the system. Negative grey relation model measures the relationship between reverse sequences. Considering the proximity of local changes and the trend of sequence development, the paper defines the relative change within the time domain and oscillation change between time intervals. So, a novel negative grey relation model is proposed both vertically and horizontally. In the end, we use the existing instance to verify the effectiveness of the model.  

Research on PEST·CRITIC-EGM(1,1) Method for Security Risk Warning of Regional Digital Economy

Fang Wang, Chengxuan Wu, Lili Liu, Jin Zhao, Yi Zhang

2023, 35(1):  49-66. 

Asbtract ( 51 )  

Related Articles | Metrics

The regional digital economy security risk warning system has been established to strengthen the construction of safety shields for the regional digital economy and promote the sound and steady development of the digital economy. Based on the PEST analysis method, a regional digital economy security risk evaluation index system including four first-level indicators, 13 second-level indicators, and 49 third-level indicators are constructed. The index weight is determined by CRITIC method, the regional digital economy security risk index (DESRI) is established by integrated operation, and the prediction and early warning are realized by EGM(1,1) model. Through the data collection and empirical analysis of Shaanxi Province, it is found that: (1) The DESRI of Shaanxi Province showed an overall rising trend from 2017 to 2020, but the risk level was reduced from dangerous to a general level; (2) In 2021 and 2022, the security risk of the digital economy in Shaanxi Province is generally at the security level, among which the policy risk index and social risk index were at the security level, the economic risk index was in the serious level and the crisis level respectively, and the technical risk index was in the crisis level. The results of the empirical analysis verify the feasibility and effectiveness of PEST·CRITIC-EGM(1,1) Method, which can be used for the assessment and early warning of regional digital economy risks.

Asymmetric Grey Evolutionary Game Models with The Limited Cognition

Qin Zhang, Zixin Bao, Zhigeng Fang, Sifeng Liu

2023, 35(1):  67-81. 

Asbtract ( 20 )  

Related Articles | Metrics

With limited cognition, the group of players can only estimate the range of their payoffs instead of the specific values. Then we propose the asymmetric grey evolutionary game. Via the analysis of the equilibrium of this game, the single grey belt and crossed grey belt are found. Meanwhile, besides Nash equilibrium, we find a new equilibrium. When the group of players are in the crossed grey belt, they can’t obtain more profits no matter how they change the original strategies. Because their grey expected profits are always equal to the grey average expected profits. This is a short-term equilibrium due to limited cognition. Finally, we illustrate the asymmetric grey evolutionary game to analyze the effect of psychological contract breaches on employee turnover intention.  

An Optimized Non-Equidistant Grey Model of Population Aging in Inner Mongolia Based on All Previous National Censuses

Jun Zhang, Chaofeng Shen

2023, 35(1):  82-100. 

Asbtract ( 28 )  

Related Articles | Metrics

The issue of population aging is related to the sustainable development of the future economy and society. It is necessary to conduct an in-depth analysis and prediction of the development trend of population aging. In this study, according to the small samples and non-equidistant characteristics of the data from the first to the seventh national censuses in Inner Mongolia, the fractional order non-equidistant GM(1,1) model with optimized background value (abbreviated as OBFNEGM(1,1) model) for the total population and the aging population in Inner Mongolia are established, and the system parameters of the OBFNEGM(1,1) model are calculated by using the whale optimization algorithm. The fitting results show that the mean absolution percentage error of the proposed model is lower than that of the classical non-equidistant GM(1,1) model. On this basis, in the future eighth national census, the total population, the aging population, and the proportion of the aging population in the total population are predicted, and the suggestions to deal with the aging of the population are put forward so as to adjust the corresponding policies and measures timely. 

An Extrapolation Non-Equigap Grey Model for Operation Management 

Che-Jung Chang, Wen-Li Dai, Der-Chiang Li, Chien-Chih Chen, Guiping Li

2023, 35(1):  101-112. 

Asbtract ( 26 )  

Related Articles | Metrics

Accurate short-term demand forecasting is crucial for the production plan development, but a shorter forecasting period implies that the product demands are more unstable and, thus, that ascertaining their developing trends is difficult. Therefore, using large historical observations to build forecasting models may not result in favorable forecasting performance. Prediction methods based on the latest limited data have thus become vital for maintaining management efficiency and competitive advantage. Grey system theory is a technique for resolving this difficulty. However, the conventional grey model is designed for time-series data featuring equigaps, which limits its application scope. Although in the current published research, scholars have proposed some non-equigap grey models; however, the newest datum is usually weakened to alleviate the randomness of data in these models, which may result in a larger prediction error. To conquer these shortcomings, this study introduces linear extrapolation to modeling procedures for emphasizing the importance of the newest datum and then proposes an improved non-equigap grey model. In the experiments of two real cases, the proposed method exhibits favorable forecasting performance, indicating a feasible solution for small non-equigap data forecasting.  

The Annual Sales Forecast for a Chinese Auto Parts Manufacturer Based on IGM (1,1) 

Hongying Shan, Mengyao Qin, Libin Zhang Zunyan Meng, Peiyang Peng

2023, 35(1):  113-129. 

Asbtract ( 43 )  

Related Articles | Metrics

Sales forecasts for auto parts manufacturers are critical to the overall health and sustainability of the auto industry. As a result, it has become critical to design a convenient and accurate forecasting model based on little historical data. By examining a modest amount of valid data, gray prediction theory can investigate the law of change. The Improved Grey Model (1,1) (IGM (1,1)) model is introduced in this study, which conducts a functional transformation on the original data series in order to create a new one with a high degree of smoothness. A genetic algorithm is utilized to establish the optimal parameter values for the background values, which enhances prediction accuracy. The model's predictive accuracy was evaluated using the annual sales of Company B, a Changchun-based auto parts manufacturer, from 2009 through 2020. The numerical findings indicate that the proposed method outperforms the four models regarding forecasting performance. Additionally, the proposed method is critical for conducting in-depth research, promoting, and implementing the gray model in auto parts manufacturing firms.  

A Laspeyres Index Decomposition-based Multivariable Grey Prediction Model for Forecasting Energy Consumption: A Case Study of Ghana

Jeffrey Ofosu-Adarkwa, Naiming Xie

2023, 35(1):  130-155. 

Asbtract ( 31 )  

Related Articles | Metrics

Energy consumption is closely linked to a country’s economic activity. For most developing countries making efforts to shift to industry-driven economies, the relationship between energy consumption and economic activity cannot be overemphasized. This study, therefore, employs the Laspeyres Index Decomposition (LID) analysis to decompose the change in energy demand into five driving factors according to three effects. The derived factors are then combined with the first order multivariable grey forecast model to form the hybrid model, LID-GM(1,6). The model is applied to the energy consumption situation of Ghana as a case study. The decomposition analysis gives insight into which economic sectors are accountable for the energy demand changes that occurred during the period 2006–2019, and thus serves as a guide for policymaking. The significance of this paper lies in its contribution to the development of the GM(1,N) prediction models. The grey forecast model, based on factors derived from an index decomposition analysis, is used to predict total energy consumed annually in Ghana from 2020 to 2030. The LID-GM(1,6) is evaluated for forecast accuracy and compared with other models. The LID-GM(1,6) has an out-of-sample MAPE of 3.77%, signifying an accuracy of approximately 96%.  

An Improved Grey Incidence Clustering Approach for Technological Innovation Capability Assessment of China's Regional High-Tech Industry

Xu Dong-Liang

2023, 35(1):  156-172. 

Asbtract ( 40 )  

Related Articles | Metrics

The development level of the high-tech industry affects the comprehensive competitiveness of a country and a region. It has great theoretical and practical significance to grasp the status quo and differences in technological innovation capability of regional high-tech industries in R&D and transformation and to provide a basis for relevant departments to formulate differentiated policies for developing high-tech industries. In order to comprehensively reflect the innovation capability and fully excavate and extract the differentiated information of China's regional high-tech industry. According to the characteristics and laws of panel data on the high-tech industry, from the two dimensions of technology R&D and achievement transformation, the grey incidence analysis method is exploited to a novel grey matrix type incidence clustering model based on the panel data for hightech innovation capability assessment and differences extraction. The result shows that the high-tech innovation capability is not strong on the whole, and there are obvious regional differences and imbalances in R&D and transformation, the ranking is in the order of eastern, central, and northwestern provinces and cities.