Accurate forecasting results are crucial for increasing energy efficiency and lowering energy consumption in wind energy.Big data and artificial intelligence(AI)have great potential in wind energy forecasting.Although...Accurate forecasting results are crucial for increasing energy efficiency and lowering energy consumption in wind energy.Big data and artificial intelligence(AI)have great potential in wind energy forecasting.Although the literature on this subject is extensive,it lacks a comprehensive research status survey.In identifying the evolution rules of big data and AI methods in wind energy forecasting,this paper summarizes the studies on big data and AI in wind energy forecasting over the last two decades.The existing big data types,analysis techniques,and forecasting methods are classified and sorted by combining literature reviews and scientometrics methods.Furthermore,the research trend of wind energy forecasting methods is determined based on big data and artificial intelligence by combing the existing research hotspots and frontier progress.Finally,this paper summarizes existing research’s opportunities,challenges,and implications from various perspectives.The research results serve as a foundation for future research and promote the further development of wind energy forecasting.展开更多
The emergence and growing popularity of Bitcoins have attracted the attention of the financial world.However,few empirical studies have considered the inclusion of the newly emerged commodity asset in the global commo...The emergence and growing popularity of Bitcoins have attracted the attention of the financial world.However,few empirical studies have considered the inclusion of the newly emerged commodity asset in the global commodity market.It is of great importance for investors and policymakers to take advantage of this asset and its potential benefits by incorporating it as a part of the broad commodity trading portfolio.In this study,we propose a novel ensemble portfolio optimization(NEPO)framework utilized for broad commodity assets,which integrates a hybrid variational mode decomposition-bidirectional long short-term memory deep learning model for future returns forecast and a reinforcement learning-based model for optimizing the asset weight allocation.Our empirical results indicate that the NEPO framework could effectively improve the prediction accuracy and trend prediction ability across various commodity assets from different sectors.In addition,it could effectively incorporate Bitcoins into the asset pool and achieve better financial performance compared to traditional asset allocation strategies,commodity funds,and indices.展开更多
Developing effective strategies to earn excess returns in the stock market is a cutting-edge topic in the field of economics.At the same time,stock price forecasting that supports trading strategies is considered one ...Developing effective strategies to earn excess returns in the stock market is a cutting-edge topic in the field of economics.At the same time,stock price forecasting that supports trading strategies is considered one of the most challenging tasks.Therefore,this study analyzes and extracts news media data,expert comments,social opinion data,and pandemic text data using natural language processing,and then combines the data with a deep learning model to forecast future stock price patterns based on historical stock prices.An interval constraint-based trading strategy is constructed.Using data from several typical stocks in the Chinese stock market during the COVID-19 period,the empirical studies and trading simulations show,first,that the sentiment composite index and the deep learning model can improve the accuracy of stock price forecasting.Second,the interval constraint-based trading strategy based on the proposed approach can effectively enhance returns and thus,can assist investors in decision-making.展开更多
Understanding the relationship between attribute performance(AP)and customer satisfaction(CS)is crucial for the hospitality industry.However,accurately modeling this relationship remains challenging.To address this is...Understanding the relationship between attribute performance(AP)and customer satisfaction(CS)is crucial for the hospitality industry.However,accurately modeling this relationship remains challenging.To address this issue,we propose an interpretable machine learning-based dynamic asymmetric analysis(IML-DAA)approach that leverages interpretable machine learning(IML)to improve traditional relationship analysis methods.The IML-DAA employs extreme gradient boosting(XGBoost)and SHapley Additive exPlanations(SHAP)to construct relationships and explain the significance of each attribute.Following this,an improved version of penalty-reward contrast analysis(PRCA)is used to classify attributes,whereas asymmetric impact-performance analysis(AIPA)is employed to determine the attribute improvement priority order.A total of 29,724 user ratings in New York City collected from TripAdvisor were investigated.The results suggest that IML-DAA can effectively capture non-linear relationships and that there is a dynamic asymmetric effect between AP and CS,as identified by the dynamic AIPA model.This study enhances our understanding of the relationship between AP and CS and contributes to the literature on the hotel service industry.展开更多
This study investigates the application of large language models in analyzing sentiment features within the exchange rate markets.Traditional natural language processing methods,such as LDA and BERT,are effective in e...This study investigates the application of large language models in analyzing sentiment features within the exchange rate markets.Traditional natural language processing methods,such as LDA and BERT,are effective in extracting topics from text;however,they fail to assess the relative importance of these topics in relation to target exchange rates.To bridge this gap,this paper employs ChatGPT to extract topics from texts and evaluate their importance scores,further enhancing exchange rate forecasting by integrating topic importance into the sentiment analysis framework.Through empirical analysis,the superiority of ChatGPT over LDA and BERT in both topic extraction and importance assessment is demonstrated.Furthermore,this study utilizes the topic importance scores generated by ChatGPT to develop a novel interval-valued sentiment index(TIS index).This index not only accounts for the relative importance of various events influencing exchange rate fluctuations but also captures the dynamic evolution of market sentiment within an interval.Empirical results highlight that the TIS Index significantly enhances the forecasting accuracy of interval models such as TARI and IMLP for exchange rates.These findings further demonstrate the advantages of ChatGPT in sentiment analysis within the foreign exchange market.These findings offer new insights into the application of ChatGPT in financial text research.展开更多
Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) mo...Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) models and a model average technique. First, considering model uncertainty,a set of alternative SFA models with various combinations of explanatory variables and distribution assumptions are constructed to estimate demands. Second, an average estimate from the estimated demand values is obtained using a model average technique. Finally, future demand forecasts are achieved, with the average estimates used as historical observations. An empirical application of air travel demand forecasting is implemented. The results of a forecasting performance comparison show that in addition to its ability to estimate demand, the proposed method outperforms other common methods in terms of forecasting passenger traffic.展开更多
Big data technology has revolutionized the research paradigm of economic forecasting regardless of the data source,forecasting method,or forecasting result.This study evaluates the current literature on economic forec...Big data technology has revolutionized the research paradigm of economic forecasting regardless of the data source,forecasting method,or forecasting result.This study evaluates the current literature on economic forecasting using big data and employs bibliometric approaches to offer a comprehensive analysis.Additionally,utilizing the advanced structural variation analysis technique,we can identify papers with transformative potential in this domain.This study provides valuable suggestions for enhancing scholars'understanding of significant research,novel breakthroughs,and emerging trends in the role of big data in economic forecasting.展开更多
Analyzing the underlying characteristics of trade values movements has attracted much attention in the domestic research.However,the proposed understanding of these characteristics is limited by the intrinsic complexi...Analyzing the underlying characteristics of trade values movements has attracted much attention in the domestic research.However,the proposed understanding of these characteristics is limited by the intrinsic complexity of the imports/exports.Since economic systems are naturally organized by hierarchies,a novel hierarchical model is proposed in this paper to forecast China's foreign trade.First,the foreign trade data are disaggregated from perspectives of trading partners and trading products,forming two independent hierarchical models with total exports and imports as target variables.Second,a bottom-up strategy is applied.All bottom time series are modelled by corresponding control variables according to trading theories.Forecasts for bottom time series are then combined to generate initial forecasts for total exports and imports.Finally,forecasts for total imports and exports from the two hierarchical models,plus a single VECM model are combined to generate final forecasts.Empirical experiments show that this proposed forecasting model approach significantly outperforms benchmark models and produces consistent forecasts for both total imports and exports or detailed items,which helps a lot for analyzing future trading structure evolution and making foreign trade policies.展开更多
Business survey,which starts from the microeconomic level,is a widely used short-term forecasting tool in practice.In this study,the authors examine whether foreign trade survey data collected by China’s Ministry of ...Business survey,which starts from the microeconomic level,is a widely used short-term forecasting tool in practice.In this study,the authors examine whether foreign trade survey data collected by China’s Ministry of Commerce would provide reliable forecasts of China’s foreign trade.The research procedure is designed from three perspectives including forecast information test,turning point forecast,and out-of-sample value forecast.First,Granger causality test detects whether survey data lead exports and imports.Second,business cycle analysis,a non-model based method,is performed.The authors construct composite indexes with business survey data to forecast turning points of foreign trade.Third,model-based numerical forecasting methods,including the Autoregressive Integrated Moving Average Model with Exogenous Variables(ARIMAX)and the artificial neural networks(ANNs)models are estimated.Empirical results show that survey data granger cause imports and exports,the leading composite index provides signal for changes of trade cycles,and quantitative models including survey data generate more accurate forecasts than benchmark models.It is concluded that trade survey data has excellent predictive capabilities for imports and exports,which can offer some priorities for government policy-making and enterprise decision making.展开更多
A decomposition clustering ensemble(DCE)learning approach is proposed for forecasting foreign exchange rates by integrating the variational mode decomposition(VMD),the selforganizing map(SOM)network,and the kemel extr...A decomposition clustering ensemble(DCE)learning approach is proposed for forecasting foreign exchange rates by integrating the variational mode decomposition(VMD),the selforganizing map(SOM)network,and the kemel extreme leaming machine(KELM).First,the exchange rate time series is decomposed into N subcomponents by the VMD method.Second,each subcomponent series is modeled by the KELM.Third,the SOM neural network is introduced to cluster the subcomponent forecasting results of the in-sample dataset to obtain cluster centers.Finally,each cluster's ensemble weight is estimated by another KELM,and the final forecasting results are obtained by the corresponding clusters'ensemble weights.The empirical results illustrate that our proposed DCE learning approach can significantly improve forecasting performance,and statistically outperform some other benchmark models in directional and level forecasting accuracy.展开更多
In this paper, a KELM-based ensemble learning approach, integrating Granger causality test, grey relational analysis and KELM(Kernel Extreme Learning Machine), is proposed for the exchange rate forecasting. The study ...In this paper, a KELM-based ensemble learning approach, integrating Granger causality test, grey relational analysis and KELM(Kernel Extreme Learning Machine), is proposed for the exchange rate forecasting. The study uses a set of sixteen macroeconomic variables including, import,export, foreign exchange reserves, etc. Furthermore, the selected variables are ranked and then three of them, which have the highest degrees of relevance with the exchange rate, are filtered out by Granger causality test and the grey relational analysis, to represent the domestic situation. Then, based on the domestic situation, KELM is utilized for medium-term RMB/USD forecasting. The empirical results show that the proposed KELM-based ensemble learning approach outperforms all other benchmark models in different forecasting horizons, which implies that the KELM-based ensemble learning approach is a powerful learning approach for exchange rates forecasting.展开更多
This study aimed to evaluate the therapeutic properties of the traditional Chinese medicine Xuesanqi(XSQ,from the rhizome of Polygonum amplexicaule D.Don)in treating ulcerative colitis.We hypothesized that its many ac...This study aimed to evaluate the therapeutic properties of the traditional Chinese medicine Xuesanqi(XSQ,from the rhizome of Polygonum amplexicaule D.Don)in treating ulcerative colitis.We hypothesized that its many active components can alleviate symptoms of colitis by regulating the gut microbiota,its metabolites,and various signaling pathways.To test our hypotheses,we designed a DSS-induced colitis model in C57BL/6 male mice.Apparent metrics were evaluated in each group of mice and performed histological analysis of relevant tissues.The gut microbial composition was analyzed by 16S rRNA sequencing of bacteria.Simultaneously,the SCFAs content was detected by gas chromatography,inflammatory factor secretion was evaluated by ELISA or western-blot,the expression of tight junction protein and key proteins of the MAPK signaling pathway were analyzed by western-blot.Our result showed that the treatment with XSQ alleviated significant various symptoms such as weight loss,blood in stool,and shortening of colon.In addition,XSQ treatment restored the dysregulated gut microbiota in colitis mice,increased short chain fatty acids(SCFAs)and normalized the MAPK/ERK/JNK signaling pathways,promoted expression of tight junction protein Occludin,Claudin-1,and E-cadherin proteins.Furthermore,we also observed a dose-dependent pattern in these treatment responses.These findings demonstrated the active components of XSQ is a promising new treatment platform for ulcerative colitis.展开更多
This study addresses a significant gap in the existing literature by conducting a comprehensive systematic review of the art market over the past 50 years,utilizing big data analysis and bibliometric methods.Through d...This study addresses a significant gap in the existing literature by conducting a comprehensive systematic review of the art market over the past 50 years,utilizing big data analysis and bibliometric methods.Through descriptive statistical analysis,we gained insights into research trends,influential literature,authors,academic disciplines,journals,institutions,and countries.By utilizing various bibliometric analyses,including co-citation,co-word,burstiness,time-zone,and co-cited author analyses,we unraveled the inherent logic within the literature.One significant discovery was the consistent annual increase in research interest in the art market.Notably,the focus of art market research has shifted from hedonic art prices to areas such as artist brand management,electronic art platforms,anti-money-laundering supervision,and art market efficiency.Moreover,this study highlights the impact of the COVID-19 pandemic,expediting an electronic revolution in the art market in recent years.Notably,our study is the first to comprehensively employ bibliometric methods to analyze the art market,thereby laying the groundwork for researchers interested in this field.展开更多
Understanding the characteristics of the dynamic relationship between the onshore Ren- minbi （CNY） and the offshore Renminbi （CNH） exchange rates considering the impact of some extreme events is very important and...Understanding the characteristics of the dynamic relationship between the onshore Ren- minbi （CNY） and the offshore Renminbi （CNH） exchange rates considering the impact of some extreme events is very important and it has wide implications in several areas such as hedging. For better esti- mating the dynamic relationship between CNY and CNH, the Granger-causality test and Bry-Boschan Business Cycle Dating Algorithm were employed in this paper. Due to the intrinsic complexity of the lead-lag relationships between CNY and CNH, the empirical mode decomposition （EMD） algorithm is used to decompose those time series data into several intrinsic mode function （IMF） components and a residual sequence, from high to low frequency. Based on the frequencies, the IMFs and a residual sequence are combined into three components, identified as short-term composition caused by some market activities, medium-term composition caused by some extreme events and the long-term trend.The empirical results indicate that when it only matters the short-term market activities, CNH always leads CNY; while the medium-term impact caused by those extreme events may alternate the lead-lag relationships between CNY and CNH.展开更多
Linear mixed-effects models are a powerful tool for the analysis of longitudinal data. The aim of this paper is to study model averaging for linear mixed-effects models. The asymptotic distribution of the frequentist ...Linear mixed-effects models are a powerful tool for the analysis of longitudinal data. The aim of this paper is to study model averaging for linear mixed-effects models. The asymptotic distribution of the frequentist model average estimator is derived, and a confidence interval procedure with an actual coverage probability that tends to the nominal level in large samples is developed. The two confidence intervals based on the model averaging and based on the full model are shown to be asymptotically equivalent. A simulation study shows good finite sample performance of the model average estimators.展开更多
Macroeconomic forecasting in China is essential for the government to take proper policy decisions on government expenditure and money supply,among other matters.The existing literature on forecasting Chinas macroecon...Macroeconomic forecasting in China is essential for the government to take proper policy decisions on government expenditure and money supply,among other matters.The existing literature on forecasting Chinas macroeconomic variables is unclear on the crucial issue of how to choose an optimal window to estimate parameters with rolling out-of-sample forecasts.This study fills this gap in forecasting economic growth and inflation in China,by using the rolling weighted least squares(WLS)with the practically feasible cross-validation(CV)procedure of Hong et al.(2018)to choose an optimal estimation window.We undertake an empirical analysis of monthly data on up to 30 candidate indicators(mainly asset prices)for a span of 17 years(2000-2017).It is documented that the forecasting performance of rolling estimation is sensitive to the selection of rolling windows.The empirical analysis shows that the rolling WLS with the CV-based rolling window outperforms other rolling methods on univariate regressions in most cases.One possible explanation for this is that these macroeconomic variables often suffer from structural changes due to changes in institutional reforms,policies,crises,and other factors.Furthermore,we find that,in most cases,asset prices are key variables for forecasting macroeconomic variables,especially output growth rate.展开更多
A framework based on response-dependence theory is proposed to analyze human and machine interaction patterns.The interaction is an information processing and exchanging system with agents responding to signals from t...A framework based on response-dependence theory is proposed to analyze human and machine interaction patterns.The interaction is an information processing and exchanging system with agents responding to signals from the decision perspective on multiple channels.Agents'pattern differences may emerge via a multiple-input multiple-output model on the sequential machine data.The connectivity with different decision-making factors embodies the interactive narrative features.The magnitude of the frequency response is compared in a parallel analysis.The interaction relationship will emerge in frequency response comparison.In the empirical study,we compare AlphaGo and human professional players'behaviors in the game of Go.We find a similar connectivity structure in vertical analysis and coincidences with the interaction relationship in the game.However,the response magnitude interval differs between AlphaGo and human professional players in several stimulus-response pairs.Integrated with static comparison,we find AlphaGo is more sensitive to long-term payoff changes than human professional players.The framework and empirical studies indicate that theory and techniques from cross-disciplinary can provide a perceptive and objective explanation of behavior patterns in human and machine interaction.The proposed framework might benefit scientists in research on AI ethics and machine behavior interpretation with big data techniques.展开更多
Generative AI technology,represented by ChatGPT,has sparked profound changes in a variety of fields,and undoubtedly generative AI will drive continuous reforms and innovation in the business and experience of the trav...Generative AI technology,represented by ChatGPT,has sparked profound changes in a variety of fields,and undoubtedly generative AI will drive continuous reforms and innovation in the business and experience of the travel and hospitality sectors.This article mainly explores the application of generative AI in the tourism industry based on existing literature,analyzes the constraints that may exist when it is applied in the field of tourism and hospitality,and explores future directions and opportunities for combining tourism,hospitality,and generative AI.This paper hopes to inspire scholars and practitioners to apply generative AI to tourism services,marketing and management,to explore smarter,more humane and more convenient tourism development modes and new business models,achieving high-quality development of tourism.展开更多
In the context of rapid globalization and technological innovation,this study introduces a novel evaluation standard system designed for the modern service industry.Utilizing the DPSIR(driving forces,pressures,states,...In the context of rapid globalization and technological innovation,this study introduces a novel evaluation standard system designed for the modern service industry.Utilizing the DPSIR(driving forces,pressures,states,impacts,responses)framework,this study categorizes pertinent characteristics to elucidate their roles within the service sector,enhancing understanding of the complex dynamics between environmental factors and human activities.Meanwhile,the application of the entropy weight method significantly reduces subjectivity,thereby improving the reliability and effectiveness of assessment outcomes by quantifying the informational contribution of various indicators.Furthermore,incorporating the technique for order preference by similarity to ideal solution(TOPSIS),analysis fosters a robust index system for assessing the developmental levels of China's life service industry.This study's innovative approach and its practical implications mark a significant leap in strategic decision-making and understanding of the modern service industry,offering a novel and adaptable tool for industry analysis.展开更多
The paper established a double filtering method (DFM) to visualize the skeleton industrial structure (SIS) of one economy and find its evolution rule. Different with the previous researches, this method is from a new ...The paper established a double filtering method (DFM) to visualize the skeleton industrial structure (SIS) of one economy and find its evolution rule. Different with the previous researches, this method is from a new view of industrial conjunctions combined by leading sectors to depict the industrial structure. It was proved that the leading sector selected by DFM must be key sector selected by Hirschman-Rasmussen method. Applied DFM to input-output tables of China, Japan and USA and MFA to Japan, and USA, the results analysis showed that DFM could overtake the two main shortcomings of minimum flow analysis (MFA), scratch SIS of each economy with its own characteristics, visualize the general evolution rules of the industrial structure with crisscrossed conjunctions among leading sectors.展开更多
基金This research work was partly supported by the National Natural Science Foundation of China(Grant Nos.:72101197 and 71988101)by the Fundamental Research Funds for the Central Universities(Grant No.:SK2021007).
文摘Accurate forecasting results are crucial for increasing energy efficiency and lowering energy consumption in wind energy.Big data and artificial intelligence(AI)have great potential in wind energy forecasting.Although the literature on this subject is extensive,it lacks a comprehensive research status survey.In identifying the evolution rules of big data and AI methods in wind energy forecasting,this paper summarizes the studies on big data and AI in wind energy forecasting over the last two decades.The existing big data types,analysis techniques,and forecasting methods are classified and sorted by combining literature reviews and scientometrics methods.Furthermore,the research trend of wind energy forecasting methods is determined based on big data and artificial intelligence by combing the existing research hotspots and frontier progress.Finally,this paper summarizes existing research’s opportunities,challenges,and implications from various perspectives.The research results serve as a foundation for future research and promote the further development of wind energy forecasting.
基金supported by the National Natural Science Foundation of China under Grants No.71801213 and No.71988101the National Center for Mathematics and Interdisciplinary Sciences,CAS.
文摘The emergence and growing popularity of Bitcoins have attracted the attention of the financial world.However,few empirical studies have considered the inclusion of the newly emerged commodity asset in the global commodity market.It is of great importance for investors and policymakers to take advantage of this asset and its potential benefits by incorporating it as a part of the broad commodity trading portfolio.In this study,we propose a novel ensemble portfolio optimization(NEPO)framework utilized for broad commodity assets,which integrates a hybrid variational mode decomposition-bidirectional long short-term memory deep learning model for future returns forecast and a reinforcement learning-based model for optimizing the asset weight allocation.Our empirical results indicate that the NEPO framework could effectively improve the prediction accuracy and trend prediction ability across various commodity assets from different sectors.In addition,it could effectively incorporate Bitcoins into the asset pool and achieve better financial performance compared to traditional asset allocation strategies,commodity funds,and indices.
基金partly supported by the National Natural Science Foundation of China under Grants No.72171223,No.71801213,and No.71988101the National Key R&D Program of China under Grants No.2021ZD0111204。
文摘Developing effective strategies to earn excess returns in the stock market is a cutting-edge topic in the field of economics.At the same time,stock price forecasting that supports trading strategies is considered one of the most challenging tasks.Therefore,this study analyzes and extracts news media data,expert comments,social opinion data,and pandemic text data using natural language processing,and then combines the data with a deep learning model to forecast future stock price patterns based on historical stock prices.An interval constraint-based trading strategy is constructed.Using data from several typical stocks in the Chinese stock market during the COVID-19 period,the empirical studies and trading simulations show,first,that the sentiment composite index and the deep learning model can improve the accuracy of stock price forecasting.Second,the interval constraint-based trading strategy based on the proposed approach can effectively enhance returns and thus,can assist investors in decision-making.
基金National Key R&D Program of China(Grant No.:2022YFF0903000)National Natural Science Foundation of China(Grant Nos.:72101197 and 71988101).
文摘Understanding the relationship between attribute performance(AP)and customer satisfaction(CS)is crucial for the hospitality industry.However,accurately modeling this relationship remains challenging.To address this issue,we propose an interpretable machine learning-based dynamic asymmetric analysis(IML-DAA)approach that leverages interpretable machine learning(IML)to improve traditional relationship analysis methods.The IML-DAA employs extreme gradient boosting(XGBoost)and SHapley Additive exPlanations(SHAP)to construct relationships and explain the significance of each attribute.Following this,an improved version of penalty-reward contrast analysis(PRCA)is used to classify attributes,whereas asymmetric impact-performance analysis(AIPA)is employed to determine the attribute improvement priority order.A total of 29,724 user ratings in New York City collected from TripAdvisor were investigated.The results suggest that IML-DAA can effectively capture non-linear relationships and that there is a dynamic asymmetric effect between AP and CS,as identified by the dynamic AIPA model.This study enhances our understanding of the relationship between AP and CS and contributes to the literature on the hotel service industry.
基金supported by the National Natural Science Foundation of China under Grants No.72171223,No.71988101the Youth Innovation Promotion Association of the Chinese Academy of Sciences.
文摘This study investigates the application of large language models in analyzing sentiment features within the exchange rate markets.Traditional natural language processing methods,such as LDA and BERT,are effective in extracting topics from text;however,they fail to assess the relative importance of these topics in relation to target exchange rates.To bridge this gap,this paper employs ChatGPT to extract topics from texts and evaluate their importance scores,further enhancing exchange rate forecasting by integrating topic importance into the sentiment analysis framework.Through empirical analysis,the superiority of ChatGPT over LDA and BERT in both topic extraction and importance assessment is demonstrated.Furthermore,this study utilizes the topic importance scores generated by ChatGPT to develop a novel interval-valued sentiment index(TIS index).This index not only accounts for the relative importance of various events influencing exchange rate fluctuations but also captures the dynamic evolution of market sentiment within an interval.Empirical results highlight that the TIS Index significantly enhances the forecasting accuracy of interval models such as TARI and IMLP for exchange rates.These findings further demonstrate the advantages of ChatGPT in sentiment analysis within the foreign exchange market.These findings offer new insights into the application of ChatGPT in financial text research.
基金supported by the National Natural Science Foundation of China under Grant Nos.71522004,11471324 and 71631008a Grant from the Ministry of Education of China under Grant No.17YJC910011
文摘Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) models and a model average technique. First, considering model uncertainty,a set of alternative SFA models with various combinations of explanatory variables and distribution assumptions are constructed to estimate demands. Second, an average estimate from the estimated demand values is obtained using a model average technique. Finally, future demand forecasts are achieved, with the average estimates used as historical observations. An empirical application of air travel demand forecasting is implemented. The results of a forecasting performance comparison show that in addition to its ability to estimate demand, the proposed method outperforms other common methods in terms of forecasting passenger traffic.
基金partly supported by the National Natural Science Foundation of China under Grants No.72171223,No.71801213,and No.71988101the National Key R&D Program of China No.2021ZD0111204.
文摘Big data technology has revolutionized the research paradigm of economic forecasting regardless of the data source,forecasting method,or forecasting result.This study evaluates the current literature on economic forecasting using big data and employs bibliometric approaches to offer a comprehensive analysis.Additionally,utilizing the advanced structural variation analysis technique,we can identify papers with transformative potential in this domain.This study provides valuable suggestions for enhancing scholars'understanding of significant research,novel breakthroughs,and emerging trends in the role of big data in economic forecasting.
基金supported by the National Natural Science Foundation of China under Grant Nos.71422015,71573251,71703156,71988101the National Center of Mathematics and Interdisciplinary Sciences+2 种基金CAS(Global Macroeconomic Monitoring,Forecasting and Policy Simulation Platform)Fujian Provincial Key Laboratory of StatisticsXiamen University under Grant No.201601。
文摘Analyzing the underlying characteristics of trade values movements has attracted much attention in the domestic research.However,the proposed understanding of these characteristics is limited by the intrinsic complexity of the imports/exports.Since economic systems are naturally organized by hierarchies,a novel hierarchical model is proposed in this paper to forecast China's foreign trade.First,the foreign trade data are disaggregated from perspectives of trading partners and trading products,forming two independent hierarchical models with total exports and imports as target variables.Second,a bottom-up strategy is applied.All bottom time series are modelled by corresponding control variables according to trading theories.Forecasts for bottom time series are then combined to generate initial forecasts for total exports and imports.Finally,forecasts for total imports and exports from the two hierarchical models,plus a single VECM model are combined to generate final forecasts.Empirical experiments show that this proposed forecasting model approach significantly outperforms benchmark models and produces consistent forecasts for both total imports and exports or detailed items,which helps a lot for analyzing future trading structure evolution and making foreign trade policies.
基金partially supported by the National Natural Science Foundation of China under Grant Nos.71422015,71988101the National Center for Mathematics and Interdisciplinary Sciences,Chinese Academy of Sciences。
文摘Business survey,which starts from the microeconomic level,is a widely used short-term forecasting tool in practice.In this study,the authors examine whether foreign trade survey data collected by China’s Ministry of Commerce would provide reliable forecasts of China’s foreign trade.The research procedure is designed from three perspectives including forecast information test,turning point forecast,and out-of-sample value forecast.First,Granger causality test detects whether survey data lead exports and imports.Second,business cycle analysis,a non-model based method,is performed.The authors construct composite indexes with business survey data to forecast turning points of foreign trade.Third,model-based numerical forecasting methods,including the Autoregressive Integrated Moving Average Model with Exogenous Variables(ARIMAX)and the artificial neural networks(ANNs)models are estimated.Empirical results show that survey data granger cause imports and exports,the leading composite index provides signal for changes of trade cycles,and quantitative models including survey data generate more accurate forecasts than benchmark models.It is concluded that trade survey data has excellent predictive capabilities for imports and exports,which can offer some priorities for government policy-making and enterprise decision making.
基金supported by the National Natural Science Foundation of China under Project No.71801213 and No.71642006the Hong Kong R&D Projects under Project No.7004715the Research Grant Council of Hong Kong under Project No.2016-3-56.
文摘A decomposition clustering ensemble(DCE)learning approach is proposed for forecasting foreign exchange rates by integrating the variational mode decomposition(VMD),the selforganizing map(SOM)network,and the kemel extreme leaming machine(KELM).First,the exchange rate time series is decomposed into N subcomponents by the VMD method.Second,each subcomponent series is modeled by the KELM.Third,the SOM neural network is introduced to cluster the subcomponent forecasting results of the in-sample dataset to obtain cluster centers.Finally,each cluster's ensemble weight is estimated by another KELM,and the final forecasting results are obtained by the corresponding clusters'ensemble weights.The empirical results illustrate that our proposed DCE learning approach can significantly improve forecasting performance,and statistically outperform some other benchmark models in directional and level forecasting accuracy.
基金Supported by the National Natural Science Foundation of China(71373262)
文摘In this paper, a KELM-based ensemble learning approach, integrating Granger causality test, grey relational analysis and KELM(Kernel Extreme Learning Machine), is proposed for the exchange rate forecasting. The study uses a set of sixteen macroeconomic variables including, import,export, foreign exchange reserves, etc. Furthermore, the selected variables are ranked and then three of them, which have the highest degrees of relevance with the exchange rate, are filtered out by Granger causality test and the grey relational analysis, to represent the domestic situation. Then, based on the domestic situation, KELM is utilized for medium-term RMB/USD forecasting. The empirical results show that the proposed KELM-based ensemble learning approach outperforms all other benchmark models in different forecasting horizons, which implies that the KELM-based ensemble learning approach is a powerful learning approach for exchange rates forecasting.
基金supported by the Natural Science Foundation of Hubei Province(2024AFD252)the Fundamental Research Funds for the Central Universities South-Central Minzu University(Grant Numbers:CZZ24017)the Fundamental Research Funds for Health Commission of Hubei Province(ZY2023M022).
文摘This study aimed to evaluate the therapeutic properties of the traditional Chinese medicine Xuesanqi(XSQ,from the rhizome of Polygonum amplexicaule D.Don)in treating ulcerative colitis.We hypothesized that its many active components can alleviate symptoms of colitis by regulating the gut microbiota,its metabolites,and various signaling pathways.To test our hypotheses,we designed a DSS-induced colitis model in C57BL/6 male mice.Apparent metrics were evaluated in each group of mice and performed histological analysis of relevant tissues.The gut microbial composition was analyzed by 16S rRNA sequencing of bacteria.Simultaneously,the SCFAs content was detected by gas chromatography,inflammatory factor secretion was evaluated by ELISA or western-blot,the expression of tight junction protein and key proteins of the MAPK signaling pathway were analyzed by western-blot.Our result showed that the treatment with XSQ alleviated significant various symptoms such as weight loss,blood in stool,and shortening of colon.In addition,XSQ treatment restored the dysregulated gut microbiota in colitis mice,increased short chain fatty acids(SCFAs)and normalized the MAPK/ERK/JNK signaling pathways,promoted expression of tight junction protein Occludin,Claudin-1,and E-cadherin proteins.Furthermore,we also observed a dose-dependent pattern in these treatment responses.These findings demonstrated the active components of XSQ is a promising new treatment platform for ulcerative colitis.
基金National Natural Science Foundation of China(Grant Nos.:72171223,71901205 and 71988101).
文摘This study addresses a significant gap in the existing literature by conducting a comprehensive systematic review of the art market over the past 50 years,utilizing big data analysis and bibliometric methods.Through descriptive statistical analysis,we gained insights into research trends,influential literature,authors,academic disciplines,journals,institutions,and countries.By utilizing various bibliometric analyses,including co-citation,co-word,burstiness,time-zone,and co-cited author analyses,we unraveled the inherent logic within the literature.One significant discovery was the consistent annual increase in research interest in the art market.Notably,the focus of art market research has shifted from hedonic art prices to areas such as artist brand management,electronic art platforms,anti-money-laundering supervision,and art market efficiency.Moreover,this study highlights the impact of the COVID-19 pandemic,expediting an electronic revolution in the art market in recent years.Notably,our study is the first to comprehensively employ bibliometric methods to analyze the art market,thereby laying the groundwork for researchers interested in this field.
基金partially supported by the National Natural Science Foundation of China under Grant Nos.71390330,71390331,71390335the National Nature Science Foundation of China for financial support to this study+1 种基金supported by the Postdoctorate Programme of Centre University of Economics and Financethe Postodctorate Programme of China Great Wall Asset Management Corporation
文摘Understanding the characteristics of the dynamic relationship between the onshore Ren- minbi （CNY） and the offshore Renminbi （CNH） exchange rates considering the impact of some extreme events is very important and it has wide implications in several areas such as hedging. For better esti- mating the dynamic relationship between CNY and CNH, the Granger-causality test and Bry-Boschan Business Cycle Dating Algorithm were employed in this paper. Due to the intrinsic complexity of the lead-lag relationships between CNY and CNH, the empirical mode decomposition （EMD） algorithm is used to decompose those time series data into several intrinsic mode function （IMF） components and a residual sequence, from high to low frequency. Based on the frequencies, the IMFs and a residual sequence are combined into three components, identified as short-term composition caused by some market activities, medium-term composition caused by some extreme events and the long-term trend.The empirical results indicate that when it only matters the short-term market activities, CNH always leads CNY; while the medium-term impact caused by those extreme events may alternate the lead-lag relationships between CNY and CNH.
文摘Linear mixed-effects models are a powerful tool for the analysis of longitudinal data. The aim of this paper is to study model averaging for linear mixed-effects models. The asymptotic distribution of the frequentist model average estimator is derived, and a confidence interval procedure with an actual coverage probability that tends to the nominal level in large samples is developed. The two confidence intervals based on the model averaging and based on the full model are shown to be asymptotically equivalent. A simulation study shows good finite sample performance of the model average estimators.
基金All remaining errors are solely ours.We acknowledge financial support from the National Natural Science Foundation of China(No.71703156)Fujian Provincial Key Laboratory of Statistics,Xiamen University(No.201601).
文摘Macroeconomic forecasting in China is essential for the government to take proper policy decisions on government expenditure and money supply,among other matters.The existing literature on forecasting Chinas macroeconomic variables is unclear on the crucial issue of how to choose an optimal window to estimate parameters with rolling out-of-sample forecasts.This study fills this gap in forecasting economic growth and inflation in China,by using the rolling weighted least squares(WLS)with the practically feasible cross-validation(CV)procedure of Hong et al.(2018)to choose an optimal estimation window.We undertake an empirical analysis of monthly data on up to 30 candidate indicators(mainly asset prices)for a span of 17 years(2000-2017).It is documented that the forecasting performance of rolling estimation is sensitive to the selection of rolling windows.The empirical analysis shows that the rolling WLS with the CV-based rolling window outperforms other rolling methods on univariate regressions in most cases.One possible explanation for this is that these macroeconomic variables often suffer from structural changes due to changes in institutional reforms,policies,crises,and other factors.Furthermore,we find that,in most cases,asset prices are key variables for forecasting macroeconomic variables,especially output growth rate.
基金supported by the National Natural Science Foundation of China(71801213,72171223 and 71988101).
文摘A framework based on response-dependence theory is proposed to analyze human and machine interaction patterns.The interaction is an information processing and exchanging system with agents responding to signals from the decision perspective on multiple channels.Agents'pattern differences may emerge via a multiple-input multiple-output model on the sequential machine data.The connectivity with different decision-making factors embodies the interactive narrative features.The magnitude of the frequency response is compared in a parallel analysis.The interaction relationship will emerge in frequency response comparison.In the empirical study,we compare AlphaGo and human professional players'behaviors in the game of Go.We find a similar connectivity structure in vertical analysis and coincidences with the interaction relationship in the game.However,the response magnitude interval differs between AlphaGo and human professional players in several stimulus-response pairs.Integrated with static comparison,we find AlphaGo is more sensitive to long-term payoff changes than human professional players.The framework and empirical studies indicate that theory and techniques from cross-disciplinary can provide a perceptive and objective explanation of behavior patterns in human and machine interaction.The proposed framework might benefit scientists in research on AI ethics and machine behavior interpretation with big data techniques.
基金Supported by National Natural Science Foundation of China(72201201,71988101)。
文摘Generative AI technology,represented by ChatGPT,has sparked profound changes in a variety of fields,and undoubtedly generative AI will drive continuous reforms and innovation in the business and experience of the travel and hospitality sectors.This article mainly explores the application of generative AI in the tourism industry based on existing literature,analyzes the constraints that may exist when it is applied in the field of tourism and hospitality,and explores future directions and opportunities for combining tourism,hospitality,and generative AI.This paper hopes to inspire scholars and practitioners to apply generative AI to tourism services,marketing and management,to explore smarter,more humane and more convenient tourism development modes and new business models,achieving high-quality development of tourism.
基金Supported by the National Key R&D Program of China(2022YFF0903000)Key Projects of Universities’Philosophy and Social Science Researches in Jiangsu Province(2025SJZD049)。
文摘In the context of rapid globalization and technological innovation,this study introduces a novel evaluation standard system designed for the modern service industry.Utilizing the DPSIR(driving forces,pressures,states,impacts,responses)framework,this study categorizes pertinent characteristics to elucidate their roles within the service sector,enhancing understanding of the complex dynamics between environmental factors and human activities.Meanwhile,the application of the entropy weight method significantly reduces subjectivity,thereby improving the reliability and effectiveness of assessment outcomes by quantifying the informational contribution of various indicators.Furthermore,incorporating the technique for order preference by similarity to ideal solution(TOPSIS),analysis fosters a robust index system for assessing the developmental levels of China's life service industry.This study's innovative approach and its practical implications mark a significant leap in strategic decision-making and understanding of the modern service industry,offering a novel and adaptable tool for industry analysis.
基金supported by the National Natural Science Foundation of China under Grant No.71173210
文摘The paper established a double filtering method (DFM) to visualize the skeleton industrial structure (SIS) of one economy and find its evolution rule. Different with the previous researches, this method is from a new view of industrial conjunctions combined by leading sectors to depict the industrial structure. It was proved that the leading sector selected by DFM must be key sector selected by Hirschman-Rasmussen method. Applied DFM to input-output tables of China, Japan and USA and MFA to Japan, and USA, the results analysis showed that DFM could overtake the two main shortcomings of minimum flow analysis (MFA), scratch SIS of each economy with its own characteristics, visualize the general evolution rules of the industrial structure with crisscrossed conjunctions among leading sectors.
