Loading...

Table of Content

    25 December 2023, Volume 35 Issue 4
    Stock Movement Prediction With Sentiment Analysis Based on Grey Exponential Smoothing Method: A Case Study on Colombo Stock Exchange, Sri Lanka
    D.M. K. N. Seneviratna , M.V.D.H.P Malawana , R. M. K. T. Rathnayaka
    2023, 35(4):  1-18. 
    Asbtract ( 85 )  
    Related Articles | Metrics
    Sentiment  Analysis  is  an  innovative  development  technique  that  uses  natural language processing techniques to derive people's emotions under positive, negative,and neutral based on public opinions of information. The main objective of this study is  to  introduce  a  novel  stock  market  prediction  method  based  on  the  Grey Exponential Smoothing method for analyzing social media data within a big-data distributed environment. The empirical investigation of this study is mainly carried out based on the stock market price indices parallel to the extracted Tweets collected during the three selected politically important moments that happened in Sri Lanka during the past ten years; the first case study is based on the political background after  the  ending  of  the  thirty  years  of  civil  war  in  years  2009.  In  the  year  2015,Maithripala Sirisena ended the dynastic rule of Mahinda Rajapaksa. So, the second case  study  has  based  the Tweets  on  the  political  reforms  done  after  the  2015 presidential  election;  the  third  study  is  based  on  the  Sri  Lankan  political  and economic  background  after  the  Rajapaksas  rose  again  in  2020.  For  validations purpose, K Nearest Neighbour, Decision Tree Model, Support Vector Machine, Grey Exponential Smoothing model, and Multinomial Naïve Bayes machine learning were considered.  According  to  the  empirical  findings,  the  new  proposed  Hybrid  Grey Exponential Smoothing model is highly accurate with the lowest RMSE error values in one-head forecasting. Furthermore, the key finding of this research suggested that the  hybrid  Grey  Exponential  Smoothing  model  performs  well  in  sentiment classification-based financial predictions than traditional methods, especially with non-stationary behavioral backgrounds.
    Grey Clustering Methods With Universal Possibility Functions
    Long Wang, Zhigeng Fang, Qin Zhang, Sifeng Liu
    2023, 35(4):  19-33. 
    Asbtract ( 64 )  
    Related Articles | Metrics
    The traditional possibility functions are always assumed to be linear functions. The preferences of decision-makers are not considered. It might not be proper to analyze all kinds of indicators with the traditional possibility functions. Therefore, we consider the preferences and first develop the universal possibility functions. The decision-makers can obtain the appropriate universal possibility functions by adjusting the clustering preference. Then, the related properties are revealed by the proof. Next, grey clustering methods with universal possibility functions are proposed. Finally, the effectiveness of the suggested methods is verified via the case illustration and comparative analysis.
    An Exponential-Polynomial Matrix Model Based on the Accumulation Generation of Ternary Interval Number Series and Its Application in Forecasting China's GDP by Region
    Lihua Ning, Fangli He, Xiangyan Zeng, Yunjie Mei, Haoze Cang
    2023, 35(4):  34-54. 
    Asbtract ( 71 )  
    Related Articles | Metrics
    Ternary interval number includes the total GDP amount in a certain period and its change range. Comprehensive information is more conducive to management decision-making. Affected by regional characteristics and national macro-control, the development trend of GDP in various regions of China in the past 15 years has been different. Some central regions grew rapidly in the early stage and fell back in the later stage, showing a saturated growth trend. Some coastal economically developed areas showed exponential growth. While some regions show an unstable upward and downward fluctuation trend. In order to predict the development trend of different GDPs, a matrix model based on exponential and polynomial regression, which can directly model the ternary interval number, is proposed in this paper. In order to eliminate the random fluctuation of data, the original ternary interval number sequence is accumulated based on the data preprocessing method in the grey model, which makes the general non-negative sequence show quasi-exponential growth so that it can be applied to the exponential-polynomial matrix model. The particle swarm optimization algorithm and the least square method are combined to estimate the parameters of the new model. The new model, quadratic polynomial, GM (1, 1), and exponential function are used to predict the GDP of 31 regions in China from 2005 to 2020. The results show that the effect of the new model is better than other models in predicting GDP for 20 regions. 
    A Novel Modeling Method of Extended Grey EGM(1,1,∑e^(ck)) Model and Its Application in Predictions
    Maolin Cheng, Bin Liu
    2023, 35(4):  55-75. 
    Asbtract ( 65 )  
    Related Articles | Metrics
    In the grey models, the GM(1,1) model is an important type of prediction model. The traditional grey GM(1,1) model has good prediction results in the case the original data show exponential variations at a slow rate. However, in practical problems, although showing exponential variations or approximately exponential variations, original data vary very fast sometimes. In these cases, the traditional grey GM(1,1) model tends to have poor prediction accuracy, mainly because the data fails to meet the laws presented by the traditional model. Therefore, the paper makes improvements in the following two aspects: first, the paper transforms the traditional accumulated generating sequence of original data; second, the paper extends the traditional grey model's structure, i.e., building a grey EGM(1,1,∑e^(ck)) model. The paper offers the parameter optimization method of the grey EGM(1,1,∑e^(ck)) model. Using the novel modeling method proposed, the paper builds the grey EGM(1,1,∑e^(ck)) models for China's total electricity consumption and China's GDP per capita, respectively, in the final section. Results show that the models built with the proposed modeling method have high simulation precision and prediction precision.
    A Multi-attribute Decision-making Method Based on Grey Correlation
    Lirong Sun, Chi Zheng, Chenkai Jiang, Yinghua Tian, Yujing Ye
    2023, 35(4):  76-90. 
    Asbtract ( 93 )  
    Related Articles | Metrics
    Aiming at the grey feature problem of ' small sample and poor information ', this paper extends the traditional analytic hierarchy process, entropy method and ' vertical and horizontal ' scatter degree method to the field of grey number, and proposes a multi-attribute decision-making method based on grey correlation. Firstly, the applicable form of index weight is enriched, and the determination method of index weight in grey number form is given systematically. Secondly, aiming at the problem that the traditional evaluation method can not be directly applied to the comprehensive evaluation with grey characteristics, a comprehensive evaluation model in the form of grey number is proposed. Finally, through the interval grey number integration method and the ' kernel and grey number ' integration method, the evaluation values under each index are formed into a comprehensive evaluation value, and the evaluation results are sorted. Compared with the traditional evaluation method, the proposed method more reflects the rationality and dynamics of the evaluation results.
    Research on Grey Clustering Model Based on NDEA for Equipment System-of-Systems Configuration Selection Decision
    Jingru Zhang, Zhigeng Fang, Shuyu Xiao, Luyue Zhang
    2023, 35(4):  91-107. 
    Asbtract ( 54 )  
    Related Articles | Metrics
    Resources (e.g., development budget, equipment performance) is not infinite for the plan and development of equipment system-of-systems (ESoS). Decision makers (DMs) must determine the priority of the ESoS configuration scheme under many constraints. Aiming for this problem, a structure and operation logic modeling of ESoS is analyzed. The network DEA approach describes each ESoS as a n-phase network decision unit with inputs and outputs. Secondly, the performance and cost of single equipment and ESoS combat effect are all considered. Based on this, we calculate the input-output efficiency of ESoS and consider two situations regarding the development budget. Then, with phased efficiency as evaluation indexes, the grey clustering evaluation based on the possibility function is applied to measure the ESoS configuration from the perspective of DMs. Finally, a case study verifies the feasibility and efficacy of the proposed methodology via selection decision results. The proposed method can aid DMs throughout the decision process for ESoS. 
    Adaptive Fluctuation Grey Model withAK Fractional Derivative for Short-term Traffic Flow Prediction
    Quntao Fu, Shuhua Mao
    2023, 35(4):  108-131. 
    Asbtract ( 93 )  
    Related Articles | Metrics
    Short-term traffic flow prediction is an essential component of intelligent transportation systems. Shallow and deep pattern learning methods have been widely applied to short-term traffic flow prediction. However, shallow learning methods struggle with highly volatile data and models are usually constant-coefficient. On the other hand, deep learning methods require significant computational resources and time. In this paper, we propose a new adaptive fluctuation grey model for short-term traffic flow prediction. We combine the fractional differential equation and fractional accumulation generation operator, and expand the GM(1,1) model using trigonometric functions. Furthermore, we improve the Harris hawks algorithm by optimizing the distribution of the initial population with Cauchy mutation operator and introducing boundary constraint handling techniques to enhance the model parameter search capability. Finally, we apply the model to short-term traffic flow parameter prediction and compare it with the benchmark model. Results indicate that the new model shows better accuracy performance and better extraction of fluctuation information. 
    A Novel Logistic Multivariate Grey Prediction Model for Energy Consumption: A case study of China Coal 
    Sihao Chen, Yongshan Liu, Huiming Duan
    2023, 35(4):  132-153. 
    Asbtract ( 170 )  
    Related Articles | Metrics
    Coal consumption plays a pivotal role in the national economic growth, and the coal-based energy supply system as the main guarantee of China's energy is impossible to change in the short term. In order to ensure the security of China's energy supply, accurate coal consumption forecast can provide important theoretical basis for the development of scientific and effective energy planning and decision-making. Starting from the classical Logistic model, this paper introduces a variety of related factors such as energy consumption, economic growth rate and carbon dioxide emission growth rate to expand the modeling objects of the Logistic model and improve the performance of the model by relying on its ability to capture the historical trend of the data model and accurately predict the future value. At the same time, a new logistic multivariate grey prediction model of energy consumption is established by introducing the principle of grey variance information organically combined with the logistic model. The modeling steps of the model are obtained by using mathematical methods such as least squares estimation of parameters and number multiplication transformation. Finally, the new model is applied to the prediction of Chinese coal consumption, and the validity of the model is verified from different perspectives of three cases, showing that the fitted and predicted data of the new model have good consistency with the actual results. The new model has a high accuracy for China's coal short-term forecast, and uses simulation and prediction effects of 1.68220% and 1.29866%, respectively, to effectively forecast China's coal consumption in 2022-2026, and points out the development trend of Chinese coal consumption, and provides a basis for China to make scientific and effective energy planning and decision-making.
    Improved Fractional Order Single Optimization Parameter Grey Model
    Jiangtao Wei, Yonghong Wu
    2023, 35(4):  154-171. 
    Asbtract ( 245 )  
    Related Articles | Metrics
    Some grey prediction models suffer from outliers and overfitting, and their prediction performance can be improved. Based on the fractional grey model (FGM) and the fractional time delayed grey model (FTDGM), an improved fractional single optimization parameter grey model (IFSGM) is proposed in this paper. A timetranslation power term is used to reduce model overfitting. The data is pre-processed to reduce the influence of outliers based on data transformation in cumulants and summations. The convolutional computational formulation is used to perform the prediction and improve the prediction effect. The genetic optimization algorithm is used to optimize the order of the fractional cumulants, find the optimal value of the order, and improve the model fit and prediction effect. In 6 data sets, the IFSGM and the 7 grey models are compared and tested. The experimental results show that IFSGM achieves excellent prediction performance. 
    On Grey Weighted Central Moving Average Model and Its Application
    Sifeng Liu, Zurun Xu, Liangyan Tao, Yingjie Yang
    2023, 35(4):  172-182. 
    Asbtract ( 60 )  
    Related Articles | Metrics
    The idea and method of weight vector group of kernel clustering have been combined with the central moving average model and grey system prediction model in response to the problems existing in the traditional moving average formula. A grey-weighted central moving average model was proposed in this paper. In the modeling process of the grey-weighted center moving average model, the number of moving average terms should be determined first, and the weight vector should be set according to the rules of weight setting for each component of the weight vector group of kernel clustering. Next, the weighted center moving average formula can be used to calculate the moving average simulation value, and the simulation errors were analyzed. Then, the grey system prediction model is applied to obtain a set of predicted values for the studied time series data. Finally, based on actual data and the predicted values of the grey system model, the required predicted values are calculated using the weighted center moving average formula. The new model can effectively solve the problem of serious lag in the simulation and prediction results of the simple moving average formula and the weighted moving average formula and also overcome the shortcomings of the center moving average model and the weighted center moving average model, which cannot be used to predict future changes due to the need for data on both sides of the "center" yt during calculation. From the simulation and prediction results of China's invention patent authorization volume, it can be seen that the new model has obvious advantages.