本文聚焦于金融风险管理的统计预测,运用VaR理论结合蒙特卡洛模拟,对金融风险进行了量化分析。研究中,以上证指数数据为样本,精确计算了上证指数的VaR值。基于资产定价理论,结合沪深市场数据,深入剖析了关键风险因子,并利用时间序列预...本文聚焦于金融风险管理的统计预测,运用VaR理论结合蒙特卡洛模拟,对金融风险进行了量化分析。研究中,以上证指数数据为样本,精确计算了上证指数的VaR值。基于资产定价理论,结合沪深市场数据,深入剖析了关键风险因子,并利用时间序列预测模型(如SMA)预测了主要股票指数的未来趋势及潜在亏损风险。此外,我们还创新性地引入社交媒体金融舆情分析,通过微博热搜数据评估社会风险系数,拓宽了风险监测的维度。在贵金属与外汇市场方面,我们同样进行了详尽的风险系数计算,剔除了市场正常波动,确保分析的准确性和针对性。基于上述综合分析,我们构建了一个集成化的金融风险反应模型,并利用Matlab平台结合机器学习技术,设计了一套金融证券风险反应程序。该程序能够实时接入证券等相关数据,对当前金融风险进行精确计算和深入分析,为金融业的稳健发展提供有力的指导和风险防范措施。This paper focuses on the statistical prediction of financial risk management, and uses VaR theory combined with Monte Carlo simulation to quantitatively analyze financial risks. In the study, the VaR value of the Shanghai Composite Index was accurately calculated using the Shanghai Composite Index data as a sample. Based on the asset pricing theory, combined with the Shanghai and Shenzhen market data, the key risk factors are analyzed in depth, and the future trend and potential loss risk of the main stock indexes are predicted by using the time series prediction model (such as SMA). In addition, we also innovatively introduce social media financial public opinion analysis, and evaluate the social risk coefficient through Weibo hot search data, which broadens the dimension of risk monitoring. In the precious metals and foreign exchange market, we also carried out a detailed calculation of the risk coefficient, eliminating the normal fluctuations in the market to ensure the accuracy and pertinence of the analysis. Based on the above comprehensive analysis, we construct an integrated financial risk response model, and use Matlab platform combined with machine learning technology to design a set of financial securities risk response program. The program can access securities and other related data in real time, accurately calculate and deeply analyze the current financial risks, and provide strong guidance and risk prevention measures for the steady development of the financial industry.展开更多
Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting d...Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting debris flow have been proposed, however, the accuracy of these methods is not high enough for practical use because of the stochastic and non-linear characteristics of debris flow. Artificial neural network has proven to be feasible and useful in developing models for nonlinear systems. On the other hand, predicting the future behavior based on a time series of collected historical data is also an important tool in many scientific applications. In this study we present a three-layer feed-forward neural network model to forecast surge of debris flow according to the time series data collected in the Jiangjia Ravine, situated in north part of Yunnan Province of China. The simulation and prediction of debris flow using the proposed approach shows this model is feasible, however, further studies are needed.展开更多
Using numerical model simulations, global surface temperature is projected to increase by l^C to 4~C during the 21 st century, primarily as a result of increasing concentrations of greenhouse gases. In the present stu...Using numerical model simulations, global surface temperature is projected to increase by l^C to 4~C during the 21 st century, primarily as a result of increasing concentrations of greenhouse gases. In the present study, a predictive technique incorporating driving forces into an observation time series was used to project the global mean surface temperature under four representative sce- narios of future emissions over the 21st century.展开更多
We have studied why PA （post-annealing） takes a long time to restore damaged crystallinity, which corresponds to repeat 10 10 times of lattice vibrations. Using a MD （molecular dynamics） simulation, we monitored t...We have studied why PA （post-annealing） takes a long time to restore damaged crystallinity, which corresponds to repeat 10 10 times of lattice vibrations. Using a MD （molecular dynamics） simulation, we monitored the time-series of the LRO （long-range order） parameter as LRO pattern, in the case of a type IIa diamond, from the beginning of ion impact by a sub-keV N2 beam implantation to a few nanoseconds, i.e., close to the feasible time limit for MD simulations. Due to the ion impact, the LRO parameter changed gradually from ＂LRO = 1＂ （crystal） to ＂LRO = 0＂ （amorphous）, showing the so-called critical slowing-down phenomenon. However, since PA was started the LRO pattern was not unique. The LRO patterns were grouped into more than three types of phases and the transition between them was also found. From the viewpoint of statistical dynamics, such chaotic variations in the LRO pattern may present that the system is a GCM （globally coupled map） of a complex system in a closed system. A GCM composed of coupled oscillators develops slowly to exhibit several different phases or ‘chaotic itinerancy＇ over time. Therefore, the long duration required for PA may be attributable to the nature of a complex system.展开更多
Empirical studies have shown that a large number of financial asset returns exhibit fat tails （leptokurtosis） and are often characterized by volatility clustering and asymmetry. This paper considers the ability of t...Empirical studies have shown that a large number of financial asset returns exhibit fat tails （leptokurtosis） and are often characterized by volatility clustering and asymmetry. This paper considers the ability of the GARCH-Type （Generalized Autoregressive Conditional Heteroskedasticity） models to capture the stylized features of volatility in national stock market returns for three countries （Portugal, Spain and Greece）. The results of this paper suggest that in the presence of asymmetric responses to innovations in the market, the ARMA （1,1）-GJRGARCH（1,1） skewed Student-t model which accommodates both the skewness and the kurtosis of financial time series is preferred.展开更多
Resonance may occur when the periods of incoming waves are close to the eigen-periods of harbor basin.The amplified waves by resonance in harbor will induce serious wave hazards to harbor structures and vehicles in it...Resonance may occur when the periods of incoming waves are close to the eigen-periods of harbor basin.The amplified waves by resonance in harbor will induce serious wave hazards to harbor structures and vehicles in it.Through traditional theoretical approaches,the eigen-periods of harbor basin with regular shapes can be obtained.In our study,we proposed a numerical model to simulate the behavior characteristics of the harbor waves.A finite difference numerical model based on the shallow water equations(SWE) is developed to simulate incoming tsunami and tidal waves.By analyzing the time series data of water surface wave amplitude variations at selected synthetic observation locations,we estimate the wave height and arrival time in coastal area.Furthermore,we use frequency spectrum analysis to investigate the natural frequencies from the data recorded at the synthetic observation stations.展开更多
文摘本文聚焦于金融风险管理的统计预测,运用VaR理论结合蒙特卡洛模拟,对金融风险进行了量化分析。研究中,以上证指数数据为样本,精确计算了上证指数的VaR值。基于资产定价理论,结合沪深市场数据,深入剖析了关键风险因子,并利用时间序列预测模型(如SMA)预测了主要股票指数的未来趋势及潜在亏损风险。此外,我们还创新性地引入社交媒体金融舆情分析,通过微博热搜数据评估社会风险系数,拓宽了风险监测的维度。在贵金属与外汇市场方面,我们同样进行了详尽的风险系数计算,剔除了市场正常波动,确保分析的准确性和针对性。基于上述综合分析,我们构建了一个集成化的金融风险反应模型,并利用Matlab平台结合机器学习技术,设计了一套金融证券风险反应程序。该程序能够实时接入证券等相关数据,对当前金融风险进行精确计算和深入分析,为金融业的稳健发展提供有力的指导和风险防范措施。This paper focuses on the statistical prediction of financial risk management, and uses VaR theory combined with Monte Carlo simulation to quantitatively analyze financial risks. In the study, the VaR value of the Shanghai Composite Index was accurately calculated using the Shanghai Composite Index data as a sample. Based on the asset pricing theory, combined with the Shanghai and Shenzhen market data, the key risk factors are analyzed in depth, and the future trend and potential loss risk of the main stock indexes are predicted by using the time series prediction model (such as SMA). In addition, we also innovatively introduce social media financial public opinion analysis, and evaluate the social risk coefficient through Weibo hot search data, which broadens the dimension of risk monitoring. In the precious metals and foreign exchange market, we also carried out a detailed calculation of the risk coefficient, eliminating the normal fluctuations in the market to ensure the accuracy and pertinence of the analysis. Based on the above comprehensive analysis, we construct an integrated financial risk response model, and use Matlab platform combined with machine learning technology to design a set of financial securities risk response program. The program can access securities and other related data in real time, accurately calculate and deeply analyze the current financial risks, and provide strong guidance and risk prevention measures for the steady development of the financial industry.
文摘Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting debris flow have been proposed, however, the accuracy of these methods is not high enough for practical use because of the stochastic and non-linear characteristics of debris flow. Artificial neural network has proven to be feasible and useful in developing models for nonlinear systems. On the other hand, predicting the future behavior based on a time series of collected historical data is also an important tool in many scientific applications. In this study we present a three-layer feed-forward neural network model to forecast surge of debris flow according to the time series data collected in the Jiangjia Ravine, situated in north part of Yunnan Province of China. The simulation and prediction of debris flow using the proposed approach shows this model is feasible, however, further studies are needed.
基金supported by the National Natural Science Foundation of China (Grant Nos.40890052 and 41275087)
文摘Using numerical model simulations, global surface temperature is projected to increase by l^C to 4~C during the 21 st century, primarily as a result of increasing concentrations of greenhouse gases. In the present study, a predictive technique incorporating driving forces into an observation time series was used to project the global mean surface temperature under four representative sce- narios of future emissions over the 21st century.
文摘We have studied why PA （post-annealing） takes a long time to restore damaged crystallinity, which corresponds to repeat 10 10 times of lattice vibrations. Using a MD （molecular dynamics） simulation, we monitored the time-series of the LRO （long-range order） parameter as LRO pattern, in the case of a type IIa diamond, from the beginning of ion impact by a sub-keV N2 beam implantation to a few nanoseconds, i.e., close to the feasible time limit for MD simulations. Due to the ion impact, the LRO parameter changed gradually from ＂LRO = 1＂ （crystal） to ＂LRO = 0＂ （amorphous）, showing the so-called critical slowing-down phenomenon. However, since PA was started the LRO pattern was not unique. The LRO patterns were grouped into more than three types of phases and the transition between them was also found. From the viewpoint of statistical dynamics, such chaotic variations in the LRO pattern may present that the system is a GCM （globally coupled map） of a complex system in a closed system. A GCM composed of coupled oscillators develops slowly to exhibit several different phases or ‘chaotic itinerancy＇ over time. Therefore, the long duration required for PA may be attributable to the nature of a complex system.
文摘Empirical studies have shown that a large number of financial asset returns exhibit fat tails （leptokurtosis） and are often characterized by volatility clustering and asymmetry. This paper considers the ability of the GARCH-Type （Generalized Autoregressive Conditional Heteroskedasticity） models to capture the stylized features of volatility in national stock market returns for three countries （Portugal, Spain and Greece）. The results of this paper suggest that in the presence of asymmetric responses to innovations in the market, the ARMA （1,1）-GJRGARCH（1,1） skewed Student-t model which accommodates both the skewness and the kurtosis of financial time series is preferred.
基金supported by the National Natural Science Foundation of China (Grant Nos.40574012 and 40676039)National Basic Research Program of China(Grant No. 2008CB425701)+1 种基金National High-tech R& D Program of China(Grant No. 2010AA012402)K. C. Wong Magna Fund in Ningbo University
文摘Resonance may occur when the periods of incoming waves are close to the eigen-periods of harbor basin.The amplified waves by resonance in harbor will induce serious wave hazards to harbor structures and vehicles in it.Through traditional theoretical approaches,the eigen-periods of harbor basin with regular shapes can be obtained.In our study,we proposed a numerical model to simulate the behavior characteristics of the harbor waves.A finite difference numerical model based on the shallow water equations(SWE) is developed to simulate incoming tsunami and tidal waves.By analyzing the time series data of water surface wave amplitude variations at selected synthetic observation locations,we estimate the wave height and arrival time in coastal area.Furthermore,we use frequency spectrum analysis to investigate the natural frequencies from the data recorded at the synthetic observation stations.
