期刊:
International Journal of Machine Learning and Cybernetics,2024年 ISSN:1868-8071
通讯作者:
Zhou, LG
作者机构:
[Zhou, Yuanyuan; Zheng, Chengli] Cent China Normal Univ, Financial Engn Res Ctr, Sch Econ & Business Adm, Wuhan 430079, Peoples R China.;[Wu, Peng] Anhui Univ, Sch Business, Hefei 230601, Peoples R China.;[Zhou, Ligang] Anhui Univ, Sch Math Sci, Hefei 230601, Peoples R China.
通讯机构:
[Zhou, LG ] A;Anhui Univ, Sch Math Sci, Hefei 230601, Peoples R China.
关键词:
Additive trapezoidal fuzzy preference relation;Priority vector;Compatibility;COWA operator;Optimization model
摘要:
Considering the conflicting opinions and different risk attitudes among decision-makers (DMs) in group decision making (GDM), this paper develops a novel compatibility model with additive trapezoidal fuzzy environment based on continuous ordered weighted averaging (COWA) operator to handle the conflicts. First, some concepts of COWA operator-based compatibility index and characteristic preference relation for additive trapezoidal fuzzy preference relation (ATFPR) are discussed. Then a compatibility reaching algorithm is designed to assist each ATFPR in achieving acceptable compatibility. Moreover, the expert weight optimization model based on the criterion of minimum compatibility of preference relation in GDM is established. Furthermore, a GDM process based on compatibility measures with ATFPRs is introduced, and an application of the proposed approach is put forward. The novelties of our approach are that: (1) COWA operator can deal with the compatibility of all arguments by using controlled parameters that consider the risk attitudes of DMs rather than the compatibility of the simply two points in intervals; (2) compatibility improving algorithm makes sure that the original opinions are retained as much as possible because only one pair of preference relation elements are revised in each round; (3) optimal weights model ensures that weights of DMs in group aggregation are determined availably.
作者机构:
[Su, Kuangxi] Xinyang Normal Univ, Sch Math & Stat, Xinyang, Peoples R China.;[Yao, Yinhong] Capital Univ Econ & Business, Sch Management & Engn, Beijing, Peoples R China.;[Zheng, Chengli] Cent China Normal Univ, Sch Econ & Business Adm, Wuhan, Peoples R China.;[Xie, Wenzhao] Changjiang Secur Co Ltd, Wuhan, Peoples R China.
通讯机构:
[Zheng, C.] S;School of Economics and Business Administration, China
关键词:
Correlation coefficient test;Empirical mode decomposition;Financial data denoising;Portfolio selection
作者机构:
[He, Feifei; Chen, Shu] Minist Water Resources China, Changjiang Water Resources Commiss, Changjiang River Sci Res Inst, Wuhan 430010, Peoples R China.;[He, Feifei; Chen, Shu] Hubei Key Lab Water Resources & Eco Environm Sci, Wuhan 430010, Peoples R China.;[He, Feifei; Chen, Shu] ChangJiang Water Resources Commiss, Res Ctr Yangtze River Econ Belt Protect & Dev Stra, Wuhan 430010, Peoples R China.;[Yang, Yuqi; Zhang, Hairong] China Yangtze Power Co Ltd, Hubei Key Lab Intelligent Yangtze & Hydroelect Sci, Yichang 443000, Peoples R China.;[Wan, Qinjuan] Cent China Normal Univ, Sch Econ & Business Adm, Wuhan 430079, Peoples R China.
通讯机构:
[Hairong Zhang] H;Hubei Key Laboratory of Intelligent Yangtze and Hydroelectric Science, China Yangtze Power Co., Ltd., Yichang 443000, China
关键词:
streamflow prediction;Bayesian model averaging;machine learning;hyperparameter optimization
摘要:
Abstract: Medium-term hydrological streamflow forecasting can guide water dispatching departments to arrange the discharge and output plan of hydropower stations in advance, which is of great significance for improving the utilization of hydropower energy and has been a research hotspot in the field of hydrology. However, the distribution of water resources is uneven in time and space. It is important to predict streamflow in advance for the rational use of water resources. In this study, a Bayesian model average integrated prediction method is proposed, which combines artificial intelligence algorithms, including long-and short-term memory neural network (LSTM), gate recurrent unit neural network (GRU), recurrent neural network (RNN), back propagation (BP) neural network, multiple linear regression (MLR), random forest regression (RFR), AdaBoost regression (ABR) and support vector regression (SVR). In particular, the simulated annealing (SA) algorithm is used to optimize the hyperparameters of the model. The practical application of the proposed model in the ten-day scale inflow prediction of the Three Gorges Reservoir shows that the proposed model has good prediction performance; the Nash–Sutcliffe efficiency NSE is 0.876, and the correlation coefficient r is 0.936, which proves the accuracy of the model. Keywords: streamflow prediction; Bayesian model averaging; machine learning; hyperparameter optimization
摘要:
Carbon dioxide (CO2) emissions and climate change risk have become constraints on global economic sustainable development. Environmental regulation (ER) is a key method for achieving synergy in CO2 and pollution reduction in China. This paper is the first study to explore the effects of ER on CO2 emissions by exploiting the National Environmental Protection 11th Five-Year Plan (NEP11-FYP). The implementation of the NEP11-FYP significantly decreases CO2 emissions by 19.73% in key environmental cities relative to other cities. Heterogeneity analyses suggest that this negative impact is larger in western cities and cities with more pressure to reduce CO2 emissions. Scale effects, structural effects, and technical effects might be three potential influencing channels through which ER contributes to the CO2 reduction effect. In addition, the results of the spatial externality of the NEP11-FYP demonstrate a positive spillover effect in neighboring cities within a distance of 300 km and a negative spillover effect in cities more than 500 km away. Our empirical findings provide policy implications for implementing low-carbon transition strategies and reducing CO2 emissions. (c) 2023 Economic Society of Australia, Queensland. Published by Elsevier B.V. All rights reserved.
期刊:
Energy Economics,2023年126:106978 ISSN:0140-9883
通讯作者:
Xu, JB
作者机构:
[Zhu, Junpeng; Wu, Shaohui] Cent China Normal Univ, Sch Econ & Business Adm, Wuhan, Peoples R China.;[Xu, JB; Xu, Junbing] Minjiang Univ, NewHuadu Business Sch, Fuzhou 361005, Fujian, Peoples R China.
通讯机构:
[Xu, JB ] M;Minjiang Univ, NewHuadu Business Sch, Fuzhou 361005, Fujian, Peoples R China.
关键词:
Abatement effect;Total emission control policy;SO (2) emissions;China
摘要:
The Total Emission Control (TEC) policy has been implemented in China for >20 years and plays a pivotal role in China's environmental governance system. Given the current reality of prominent environmental issues in China, there is ongoing controversy regarding whether the TEC policy has effectively reduced pollution as desired. Inspired by this, this paper takes the TEC policy implemented in the 11th Five Year Plan as an example, and based on the manually collected city-level SO2 emission reduction targets, we construct a difference-in-differences evaluation framework to investigate the abatement effect of the TEC policy. The results demonstrate a significant reduction in SO2 emissions resulting from the implementation of the TEC policy. A series of identification tests verify the robustness of the findings. The mechanism analysis shows that the end-of-pipe treatment and cleaner production are important channels to achieve the abatement effect, while the scale effect is deemed insignificant. Heterogeneity analysis shows that the policy effect varies significantly across different types of firms and regions. The conclusions contribute not only to a comprehensive understanding of the TEC policy, but also provide an important practical value for building a modern pollution control system and promoting the construction of ecological civilization.
摘要:
Using the first unified and stringent financial regulatory policy for the asset management industry as a quasi-natural experiment, this study identifies the causal effect of New Asset Management Regulation on corporate R & D investment by using the difference-in-differences method. We find that the implementation of NAMR can promote corporate R & D investment, which supports regulatory effectiveness. The mechanism tests show that the implementation of NAMR reduces firm financialization and alleviates financing constraints, thereby increasing corporate R & D investment. The heterogeneity tests show that this effect is more pronounced in non-state-owned enterprises, firms located in the region with a higher degree of marketization, and firms with more media attention. Overall, our findings reveal that the implementation of NAMR has positive effects on corporate R & D investment, which provides fresh insights into the positive effects of stringent financial regulation.
作者机构:
[Su, Kuangxi] Xinyang Normal Univ, Sch Math & Stat, Xinyang, Peoples R China.;[Zheng, Chengli; Yu, Xing] Cent China Normal Univ, Sch Econ & Business Adm, Wuhan, Peoples R China.
通讯机构:
[Su, KX ] X;Xinyang Normal Univ, Sch Math & Stat, Xinyang, Peoples R China.
关键词:
Portfolio allocation;Complete EEMD with adaptive noise;Financial data denoising;CEEMDAN denoising
摘要:
Effective denoising strategies are increasingly important for portfolio investors. Considering that the common ensemble empirical mode decomposition (EEMD)-based stepwise denoising algorithms suffer from white noise interference and ignore the effect of low-frequency redundant noise components on the portfolio, a novel complete EEMD with adaptive noise (CEEMDAN) denoising algorithm is proposed to improve the portfolio performance. Specifically, we apply CEEMDAN to decompose noisy prices into a series of intrinsic mode functions (IMFs). Then, a series of tests based on the correlations between the original noisy prices and the decomposed IMFs are performed to identify which IMFs are noisy modes. If the tests accept the null hypothesis, the IMFs are considered as noisy components. Finally, we use the soft-threshold technique to process the noisy components and sum the non-noisy components to construct the denoised prices. The empirical results show that under the dynamic minimum-CVaR framework, the proposed CEEMDAN denoising algorithm is not affected by white noise and outperforms the EEMD denoising and stepwise denoising algorithms in improving out-of-sample portfolio returns. Overall, the proposed CEEMDAN denoising is the optimal denoising algorithm, which can help investors improve portfolio performance to the greatest extent.
作者机构:
[Liu, Chong] Northeastern Univ, Coll Sci, Shenyang 110819, Peoples R China.;[Wu, Wen-Ze] Cent China Normal Univ, Sch Econ, Business Adm, Wuhan 430079, Peoples R China.;[Xie, Wanli] Qufu Normal Univ, Sch Commun, Rizhao 276826, Peoples R China.
通讯机构:
[Wu, W.-Z.] S;School of Economics and Business Administration, China
关键词:
Grey system theory;Multiobjective grey wolf optimizer;Time series prediction;Weakened accumulation operator
摘要:
As a combination of the differential equation prediction model and intelligent optimiza-tion algorithm, the grey intelligent prediction algorithm has attracted increasing attention due to its outstanding performance in small-sample environments. However, most studies focus only on the improvement of algorithm performance, with little regard to the uni-formity, ill-condition and overfitting of the algorithm. To promote the development of this field, we develop a new grey intelligent prediction algorithm with multiobjective correc-tion strategy based on the new weakened accumulation grey optimization model and the multiobjective grey wolf optimizer. In this new prediction algorithm, the new weakened accumulation operation is utilized to enhance the predictive ability of the algorithm and mitigate the ill-condition of the system, the Bernoulli parameter and a discretization tech-nique are used to activate the uniformity and unbiasedness of the algorithm, respectively, and the multiobjective grey wolf optimizer is employed to alleviate the overfitting of the system. Compared with the previous grey intelligent prediction models, the new prediction algorithm is more perfect and reasonable. Taking two energy datasets as research cases, the evaluation results of a system consisting of six evaluation metrics and the Diebold -Mariano test show that the proposed model outperforms the other six comparative mod-els in terms of prediction performance and stability, which confirms the feasibility and validity of the algorithm. (c) 2023 Elsevier Inc. All rights reserved.
期刊:
Decision Support Systems,2023年:114103 ISSN:0167-9236
通讯作者:
Lingli Wu
作者机构:
[Shiming Deng] School of Management, Huazhong University of Science and Technology, Luoyu Road 1037, Wuhan, 430074, China;[Rachel Chen] Graduate School of Management, University of California Davis, Davis, CA 95616, United States;School of Economics and Business Administration, Central China Normal University, Luoyu Road 152, Wuhan, 430079, China;Department of Logistics and Maritime Studies, The Hong Kong Polytechnic University, 11 Yuk Choi Road, Hung Hom, Kowloon, Hong Kong, China;[Lingli Wu] School of Economics and Business Administration, Central China Normal University, Luoyu Road 152, Wuhan, 430079, China<&wdkj&>Department of Logistics and Maritime Studies, The Hong Kong Polytechnic University, 11 Yuk Choi Road, Hung Hom, Kowloon, Hong Kong, China
通讯机构:
[Lingli Wu] S;School of Economics and Business Administration, Central China Normal University, Luoyu Road 152, Wuhan, 430079, China<&wdkj&>Department of Logistics and Maritime Studies, The Hong Kong Polytechnic University, 11 Yuk Choi Road, Hung Hom, Kowloon, Hong Kong, China
摘要:
Consumers are often uncertain about how a product fits their individual preferences before purchase. To resolve such uncertainty, firms can use fit-revelation activities such as sampling, product demonstration, and virtual showrooms. Recently, there is an emerging trend of combining product sampling with advertising (e.g., Amazon’s sampling-advertising initiative). Empirical research has shown that fit-revelation may enhance or weaken the effect of advertising. We contribute to the literature by developing an analytical model that links these interactions with the firm’s strategic decisions. We find that, interestingly, when fit-revelation enhances the effect of advertising, these two instruments are not necessarily complementary. Our study further characterizes the firm’s strategy space of whether to conduct fit-revelation alone, advertising alone, or both. We show that advertising may reverse the firm’s decision on whether to facilitate fit-revelation. Moreover, how complementarity/substitutability affects the optimal strategy depends on the types of ads. While substitutability denies the optimality of the joint strategy under informative ads, it fails to do so under persuasive ads. On the other hand, complementarity is necessary for the joint strategy to be optimal under informative ads, which is not the case under persuasive ads. Finally, we extend our analysis to targeted fit-revelation/advertising with heterogeneous consumers ex ante, in which case the firm may find it optimal to target low-valuation consumers. Given the latest trends and growing interest in the deployment of joint advertising and sampling, our study offers timely insights for practitioners.
作者机构:
[Wu, Wen-Ze] Cent China Normal Univ, Sch Econ & Business Adm, Wuhan 430079, Peoples R China.;[Hu, Zhiming] Zhejiang Gongshang Univ, Sch Math & Stat, Hangzhou 310018, Peoples R China.;[Wu, Wen-Ze] Natl Univ Singapore, NUS Business Sch, 21 Lower Kent Rd, Singapore S119077, Singapore.;[Qi, Qin] Tongji Univ, Sch Econ & Management, Shanghai 200092, Peoples R China.;[Zhang, Tao] Guangxi Univ Sci & Technol, Sch Sci, Liuzhou 545006, Peoples R China.
通讯机构:
[Zhiming Hu] S;School of
Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou, China<&wdkj&>Zhejiang College, Shanghai University of Finance and Economics, Jinhua, China
摘要:
Purpose
Drawing on the dual-strategies theory of social rank and leader distance theory, this paper aims to investigate the influence of supervisor bottom-line mentality (BLM) on employee knowledge-related behaviors by considering the mediating role of perceived leader prestige or dominance and the moderating role of supervisor–subordinate guanxi (SSG).
Design/methodology/approach
This study collected survey data from 185 research and development employees in East China at three-time points. The authors conducted path analysis and bootstrapping-based analytic approach to test the hypotheses by Mplus7.0.
Findings
The results showed that supervisor BLM has a negative effect on employee knowledge sharing and a positive effect on knowledge hiding. Besides, perceived leader prestige or dominance mediated the relationship between supervisor BLM and employee knowledge hiding. Furthermore, SSG moderated the relationship between supervisor BLM and perceived leader prestige or dominance, as well as the indirect effects of supervisor BLM on knowledge hiding via perceived leader prestige or dominance.
Originality/value
There is limited research on investigating the influence of supervisor BLM in the field of knowledge management. The authors carried out this study to provide evidence of how and when supervisor BLM affects employee knowledge sharing and hiding.