Query：
学者姓名：卓杏轩
Refining：
Year
Type
Indexed by
Source
Complex
Former Name
Co-
Language
Clean All
Abstract ：
As the Belt and Road Initiative (BRI) continues to advance, trade networks among BRI countries have evolved significantly. Understanding development patterns within these trade networks is crucial for promoting further growth. This study adopts a spatiotemporal perspective to analyze the dynamic evolution and driving factors of trade networks among BRI countries, utilizing the Separable Temporal Exponential Random Graph Model (STERGM) and a change point detection model. These methods assess the impact of endogenous structural variables, exogenous edge-level covariates, and exogenous nodal variables on the formation and dissolution of trade networks, as well as on stage-specific changes within these networks. The findings reveal that: (1) around 2017, the trade networks underwent a significant shift, with high-trade-value relationships growing faster than low-trade-value ones, and the networks have a small-world character. (2) China, Turkey, India, and Russia hold central positions in the trade networks, functioning as "bridges" and "hubs"; the prominence of Poland, the Czech Republic, and Ukraine has increased, while Thailand and United Arab Emirates have seen a relative decline; (3) geographical proximity, bilateral investment treaties, and shared legal origins foster trade network development, whereas exchange rate volatility and political distance have a negative impact. Countries with high urbanization, large populations, and strong economies are more likely to form trade relations. And these effects on the formation and maintenance of trade relations changed significantly before and after 2017. Therefore, while enhancing their own economic and social development, BRI countries should work to strengthen trade relations by bridging political differences and establishing trade agreements.
Keyword ：
Change-point detection Change-point detection Graph Model Graph Model Separable Temporal Exponential Random Separable Temporal Exponential Random The Belt and Road initiative The Belt and Road initiative Trade networks Trade networks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhuo, Xingxuan , Lin, Liuqing , Lian, Jiefan . Spatiotemporal analysis of the dynamic evolution and driving factors of trade networks in the Belt and Road countries [J]. | SOCIAL NETWORKS , 2025 , 82 : 80-98 . |
| MLA | Zhuo, Xingxuan 等. "Spatiotemporal analysis of the dynamic evolution and driving factors of trade networks in the Belt and Road countries" . | SOCIAL NETWORKS 82 (2025) : 80-98 . |
| APA | Zhuo, Xingxuan , Lin, Liuqing , Lian, Jiefan . Spatiotemporal analysis of the dynamic evolution and driving factors of trade networks in the Belt and Road countries . | SOCIAL NETWORKS , 2025 , 82 , 80-98 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Forecasting cargo throughput is an essential albeit challenging task for national and port optimisation decision-making, resource allocation, and control planning. To this end, a novel forecasting model is developed for mixed-frequency data called attention-DeepAR-MIDAS (ADM) by introducing the mixed data sampling (MIDAS) technique and attention mechanism into the DeepAR forecasting algorithm in this study. The proposed ADM model is specifically designed with an attention mechanism to accurately identify and prioritise the most influential variables, both endogenous and exogenous, over time. Hence, it can effectively use the nonlinear information of mixed-frequency data, which is conducive to port throughput forecasting. Furthermore, the ADM model possesses both long-term and short-term high-precision forecasting capabilities, enabling multi-step probability forecasting and better tracking of abnormal changes in endogenous and exogenous variables of port throughput, fitting their fluctuation trends. By analysing the differences in model performance before and after improvement based on forecast accuracy metrics, probability interval testing, and DM testing methods, the ADM model achieves accurate forecasting. Finally, China's monthly port throughput forecast results also illustrate the superiority of the ADM model, which provides decision-makers with more timely, accurate, and comprehensive forecasts.
Keyword ：
machine learning machine learning mixed-frequency data mixed-frequency data nonlinearity nonlinearity port throughput forecasting port throughput forecasting time-series time-series
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Shao, Bo , Su, Xiaoli , Li, Xin et al. Mixed-frequency data-driven forecasting port throughput: a novel attention-DeepAR-MIDAS model [J]. | INTERNATIONAL JOURNAL OF SHIPPING AND TRANSPORT LOGISTICS , 2025 , 20 (3) . |
| MLA | Shao, Bo et al. "Mixed-frequency data-driven forecasting port throughput: a novel attention-DeepAR-MIDAS model" . | INTERNATIONAL JOURNAL OF SHIPPING AND TRANSPORT LOGISTICS 20 . 3 (2025) . |
| APA | Shao, Bo , Su, Xiaoli , Li, Xin , Zhuo, Xingxuan . Mixed-frequency data-driven forecasting port throughput: a novel attention-DeepAR-MIDAS model . | INTERNATIONAL JOURNAL OF SHIPPING AND TRANSPORT LOGISTICS , 2025 , 20 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
High-frequency macro-financial environment variables provide more useful information and are efficient in predicting the low-frequency GDP growth rate. To this end, we extend the traditional Growth-at-Risk (GaR) into a high-frequency GaR (HF-GaR). In this extension, we construct three high-frequency macro-financial environment indices using a mixed frequency dynamic factor model and then use a mixed data sampling-quantile regression method to measure China's daily GaR from Jan 1, 2000, to Sep 30, 2024. The evidence shows that our HF-GaR has favorable prediction performance, with quantile mean absolute error and quantile root square error values less than 0.1 and is significantly superior to the traditional GaR at the 1% level for most quantiles. Additionally, HF-GaR can offer early warning of economic downturns, especially predicting China's GDP growth rate at the 5% quantile less than 0 in 2020Q1. Moreover, we conduct a counterfactual scenario analysis and find that the conditional quantile of GDP growth rate changes as the macro-financial environment tightens or loosens. Finally, we also validated that the HF-GaR model is equally applicable in other economies.
Keyword ：
Counterfactual scenario analysis Counterfactual scenario analysis Growth-at-Risk Growth-at-Risk MF-DFM MF-DFM MIDAS-QR MIDAS-QR Skewed t-distribution Skewed t-distribution
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Mengnan , Xu, Qifa , Jiang, Cuixia et al. High-frequency Growth-at-Risk of China: the Role of Macro-financial Environment [J]. | COMPUTATIONAL ECONOMICS , 2025 . |
| MLA | Xu, Mengnan et al. "High-frequency Growth-at-Risk of China: the Role of Macro-financial Environment" . | COMPUTATIONAL ECONOMICS (2025) . |
| APA | Xu, Mengnan , Xu, Qifa , Jiang, Cuixia , Zhuo, Xingxuan . High-frequency Growth-at-Risk of China: the Role of Macro-financial Environment . | COMPUTATIONAL ECONOMICS , 2025 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Carbon price—as a critical component in the functioning of carbon market mechanisms—plays an indispensable role in policy formulation, market development, and societal progress. Thus, accurately predicting carbon prices is of paramount importance. This study aims to comprehensively investigate the impact of unconventional events (e.g., political conflicts and extreme weather) and mixed-frequency data (e.g., daily high-frequency financial information and monthly low-frequency macroeconomic data) on carbon price forecasting; to this end, it introduces the novel Prophet-Backpropagation Neural Network-Reverse (Unrestricted) Mixed Data Sampling model, which innovatively integrates the following three key advantages: the quantification of irregular events using Prophet, nonlinear pattern recognition through a back-propagation neural network, and frequency alignment via reverse mixed data sampling. Applied to daily carbon price prediction in the Hubei carbon market, this model is statistically validated to significantly outperform other models, as demonstrated by the Diebold-Mariano test. This study's results underscore the model's superior predictive capability and elucidate the key drivers of carbon prices and their nonlinear impact mechanisms. © 2025 Elsevier Ltd
Keyword ：
Backpropagation Backpropagation Carbon Carbon Carbon Economy Carbon Economy Commerce Commerce Costs Costs Neural networks Neural networks Pattern recognition Pattern recognition Weather forecasting Weather forecasting
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhuo, Xingxuan , Zhang, Fangyun , Long, Houyin et al. Unveiling the drivers of high-frequency carbon price dynamics: A nonlinear fusion approach with irregular events and mixed-frequency data [J]. | Energy , 2025 , 335 . |
| MLA | Zhuo, Xingxuan et al. "Unveiling the drivers of high-frequency carbon price dynamics: A nonlinear fusion approach with irregular events and mixed-frequency data" . | Energy 335 (2025) . |
| APA | Zhuo, Xingxuan , Zhang, Fangyun , Long, Houyin , Lin, Feng . Unveiling the drivers of high-frequency carbon price dynamics: A nonlinear fusion approach with irregular events and mixed-frequency data . | Energy , 2025 , 335 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Given that crude oil prices are influenced by the complex interplay of political, economic, and social events, leading to rapid, substantial, and unpredictable fluctuations, the associated risk has received considerable attention. How can we quantitatively characterize the impact of these sudden events and accurately measure crude oil price risk? To achieve this objective, the paper introduces the Prophet Quantile Regression (ProphetQR) model. This model not only analyzes the impact of sudden events on crude oil prices but also evaluates the effectiveness of strategies implemented to control these fluctuations. It also forecasts the future distribution of crude oil prices and measures both the potential upside and downside risks associated with crude oil price volatility. By employing a multi-step ahead rolling forecasting approach and the proposed Prophet-QR model, this study draws several empirical conclusions. First, the Prophet-QR model demonstrates superior accuracy in prediction. Second, sudden events, such as the Iraq war and the Libyan war, have a profound impact on crude oil prices, causing the oil price at risk (OaR) to rise sharply. Third, the implementation of oil price intervention measures, such as production cuts and strategic reserve releases, is highly effective in mitigating the adverse effects of sudden events, thereby normalizing the OaR. Continuously monitoring OaR fluctuations supports informed policymaking and effectively reduces the adverse impacts of sudden events on future crude oil prices.
Keyword ：
Crude oil price Crude oil price Intervention measures Intervention measures Prophet model Prophet model Quantile regression Quantile regression Sudden events Sudden events
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhuo, Xingxuan , Ye, Jianjiang , Liu, Han et al. Analyzing dynamics of crude oil price amid sudden events and intervention measures: Insights from a Prophet-QR model [J]. | APPLIED ENERGY , 2025 , 401 . |
| MLA | Zhuo, Xingxuan et al. "Analyzing dynamics of crude oil price amid sudden events and intervention measures: Insights from a Prophet-QR model" . | APPLIED ENERGY 401 (2025) . |
| APA | Zhuo, Xingxuan , Ye, Jianjiang , Liu, Han , Lin, Feng . Analyzing dynamics of crude oil price amid sudden events and intervention measures: Insights from a Prophet-QR model . | APPLIED ENERGY , 2025 , 401 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The impact of financial conditions on Chinese macroeconomic activities has recently received considerable attention. This paper utilizes a constructed Chinese financial conditions index (FCI) to appraise the role of financial conditions in Chinese growth at risk, and further traces the influencing factors of tail risks of macroeconomic activities. The findings reveal that financial conditions may lead to an increase in future tail risks for macroeconomic activities, and financial conditions are associated more with downside risks than with upside potential. Moreover, the extension degree of financial conditions in relation to the tail risks of macroeconomic activities displays time-varying and heterogeneous characteristics. In particular, financial conditions have a more pronounced effect on the tail risks of investment growth. Additionally, this paper provides direct evidence from a financial perspective, suggesting that M2 is a common factor of the tail risks of macroeconomic activities, and treasury yields play a crucial role in tail risks related to consumption growth. Simultaneously, the real effective exchange rate of the Renminbi Yuan emerges as a vital factor in tail risks regarding import and export growth. Our results provide valuable insights for the government in addressing macroeconomic risks and formulating relevant policies.
Keyword ：
Deep GaR Deep GaR Financial conditions Financial conditions Generalized variance decompositions Generalized variance decompositions Macroeconomic activities Macroeconomic activities Tail risk Tail risk
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Han , Wang, Lijun , Zhuo, Xingxuan . Unveiling the shadows: The effects of financial conditions on the tail risks of China's macroeconomic activities [J]. | ECONOMIC ANALYSIS AND POLICY , 2024 , 85 : 1-14 . |
| MLA | Liu, Han et al. "Unveiling the shadows: The effects of financial conditions on the tail risks of China's macroeconomic activities" . | ECONOMIC ANALYSIS AND POLICY 85 (2024) : 1-14 . |
| APA | Liu, Han , Wang, Lijun , Zhuo, Xingxuan . Unveiling the shadows: The effects of financial conditions on the tail risks of China's macroeconomic activities . | ECONOMIC ANALYSIS AND POLICY , 2024 , 85 , 1-14 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper introduces a novel forecasting approach that addresses a significant challenge in applied research: effectively utilizing high-dimensional and mixed-frequency data from multiple sources to explain and predict variables that respond at high frequency. This approach combines a mixed data sampling model and group variable selection methods, resulting in the development of the Group Penalized Reverse Unrestricted Mixed Data Sampling Model (GP-RU-MIDAS). The GP-RU-MIDAS model is designed to achieve various research objectives, including analyzing mixed-frequency data in reverse, estimating high-dimensional parameters, identifying key variables, and analyzing their relative importance and sensitivity. By applying this model to uncover uncertainties in stock market returns, the following notable results emerge: (1) GP-RU-MIDAS improves the selection of relevant variables and enhances forecasting accuracy; (2) various risks impact stock market returns in diverse ways, with effects varying over time and exhibiting continuous trends, phase shifts, or extreme levels; and (3) stock market volatility and the Euro to RMB exchange rate significantly influence stock market returns over different forecasting periods, with a generally positive and dynamic impact. In conclusion, the GP-RU-MIDAS model demonstrates robustness and utility in complex data analysis scenarios, providing insights into the nuanced realm of stock market risk assessment.
Keyword ：
group penalties group penalties high-dimensional data high-dimensional data mixed data sampling model mixed data sampling model mixed-frequency data mixed-frequency data stock market returns stock market returns stock market risks stock market risks
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhuo, Xingxuan , Luo, Shunfei , Cao, Yan . Exploring Multisource High-Dimensional Mixed-Frequency Risks in the Stock Market: A Group Penalized Reverse Unrestricted Mixed Data Sampling Approach [J]. | JOURNAL OF FORECASTING , 2024 , 44 (2) : 459-473 . |
| MLA | Zhuo, Xingxuan et al. "Exploring Multisource High-Dimensional Mixed-Frequency Risks in the Stock Market: A Group Penalized Reverse Unrestricted Mixed Data Sampling Approach" . | JOURNAL OF FORECASTING 44 . 2 (2024) : 459-473 . |
| APA | Zhuo, Xingxuan , Luo, Shunfei , Cao, Yan . Exploring Multisource High-Dimensional Mixed-Frequency Risks in the Stock Market: A Group Penalized Reverse Unrestricted Mixed Data Sampling Approach . | JOURNAL OF FORECASTING , 2024 , 44 (2) , 459-473 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Historical tourism volume, search engine data, and weather calendar data have close causal relationship with daily tourism volume. However, when used in the prediction of daily tourism volume, the feature variables of the huge and complex search engine data do not have strong independence. These repetitive and highly relevant data must be analyzed and selected; otherwise, they will increase the training burden of neural network and reduce the prediction effect. This study proposes a daily tourism volume prediction model, maximum correlation minimum redundancy feature selection and long short-term memory, on the basis of feature selection and deep learning. Firstly, the multivariate high-dimensional features, including search engine data and weather factors, are selected to identify the key influencing factors. Secondly, the deep neural network is used to make a multistep forward rolling prediction of daily tourism volume. Results show that keywords of famous scenic spots, weather, historical tourism volume, and tourism strategies in the search engine data significantly improve the prediction accuracy of daily tourism volume. The proposed maximum correlation minimum redundancy feature selection and long short-term memory model performs better than other models, such as autoregressive integrated moving average, multiple regression, support vector machine, and long short-term memory.
Keyword ：
daily tourism volume prediction daily tourism volume prediction deep learning deep learning feature selection feature selection search engine data search engine data
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yin, Ming , Lu, Feiya , Zhuo, Xingxuan et al. Prediction of daily tourism volume based on maximum correlation minimum redundancy feature selection and long short-term memory network [J]. | JOURNAL OF FORECASTING , 2023 , 43 (2) : 344-365 . |
| MLA | Yin, Ming et al. "Prediction of daily tourism volume based on maximum correlation minimum redundancy feature selection and long short-term memory network" . | JOURNAL OF FORECASTING 43 . 2 (2023) : 344-365 . |
| APA | Yin, Ming , Lu, Feiya , Zhuo, Xingxuan , Yao, Wangzi , Liu, Jialong , Jiang, Jijiao . Prediction of daily tourism volume based on maximum correlation minimum redundancy feature selection and long short-term memory network . | JOURNAL OF FORECASTING , 2023 , 43 (2) , 344-365 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
A one-step forward forecasting test for carbon market pricing is done in this work, in which data from the first seven trading days is used to anticipate the price on the eighth trading day. The study compares the MAE, MSE, and RMSE values of several forecasting models and discovers that combining empirical mode decomposition (EMD) and forecasting models yields the best results. It was shown that the hybrid model can improve both the durability and accuracy of carbon price estimates. In terms of forecasting, the combined EMD-BiLSTM-ATTENTION model beats other comparator models, and carbon price forecasting errors in Hubei and Fujian are smaller than those in Shenzhen due to their more stable frequency amplitudes. Nevertheless, it has been discovered that estimating the carbon price in Shenzhen is more difficult due to higher amplitude variations, resulting in higher prediction errors. Overall, the findings indicate that the proposed EMD-BiLSTM-ATTENTION model is appropriate for carbon price prediction, and the study includes carbon market price prediction maps for Shenzhen, Hubei, and Fujian. © 2023 IEEE.
Keyword ：
Carbon Carbon Commerce Commerce Empirical mode decomposition Empirical mode decomposition Forecasting Forecasting Long short-term memory Long short-term memory
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Tong , Li, Shilun , Lin, Feng et al. Carbon Price Prediction based on EMD-BiLSTM-ATTENTION model [C] . 2023 : 90-94 . |
| MLA | Li, Tong et al. "Carbon Price Prediction based on EMD-BiLSTM-ATTENTION model" . (2023) : 90-94 . |
| APA | Li, Tong , Li, Shilun , Lin, Feng , Zhuo, Xingxuan . Carbon Price Prediction based on EMD-BiLSTM-ATTENTION model . (2023) : 90-94 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Under the combined effects of inventory-level-dependent demand (ILDD) and trade credit, the retailer is able to order more quantities to stimulate market demand. However, from the supplier's perspective, two important issues are lacking sufficient attention. First, during the credit period, the retailer's higher order quantities imply increases in both the retailer's account payable and the supplier's opportunity cost of capital. Second, given the supplier's fixed production rate, the increased market demand may drive the capacity utilization to be variable. Thus, by formulating a supplier-dominated system, this paper incorporates trade credit limit (TCL) to address its effects on optimal policies vis-à-vis the item with ILDD. Specifically, three indicators can be proposed to reveal which type of financing policy the retailer should choose. Moreover, based on TCL, the supplier can effectively manage the retailer's order quantity and the corresponding account payable. Additionally, the retailer's maximum allowable order quantity is developed to ensure that the supplier can supply the retailer's order quantity on time. Furthermore, when the effects of ILDD become more significant, the manufacturer will reduce the maximum allowable order quantity to control the retailer's order incentive. © 2023 China Science Publishing & Media Ltd.
Keyword ：
Delay in payments Delay in payments Inventory-level-dependent demand Inventory-level-dependent demand Order policy Order policy Supplier-dominated channel Supplier-dominated channel Trade credit limit Trade credit limit
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, F. , Shi, Y. , Zhuo, X. . Optimizing order policy and credit term for items with inventory-level-dependent demand under trade credit limit [J]. | Journal of Management Science and Engineering , 2023 , 8 (4) : 413-429 . |
| MLA | Lin, F. et al. "Optimizing order policy and credit term for items with inventory-level-dependent demand under trade credit limit" . | Journal of Management Science and Engineering 8 . 4 (2023) : 413-429 . |
| APA | Lin, F. , Shi, Y. , Zhuo, X. . Optimizing order policy and credit term for items with inventory-level-dependent demand under trade credit limit . | Journal of Management Science and Engineering , 2023 , 8 (4) , 413-429 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
