Traffic flow prediction,as the basis of signal coordination and travel time prediction,has become a research point in the field of transportation.For traffic flow prediction,researchers have proposed a variety of meth...Traffic flow prediction,as the basis of signal coordination and travel time prediction,has become a research point in the field of transportation.For traffic flow prediction,researchers have proposed a variety of methods,but most of these methods only use the time domain information of traffic flow data to predict the traffic flow,ignoring the impact of spatial correlation on the prediction of target road segment flow,which leads to poor prediction accuracy.In this paper,a traffic flow prediction model called as long short time memory and random forest(LSTM-RF)was proposed based on the combination model.In the process of traffic flow prediction,the long short time memory(LSTM)model was used to extract the time sequence features of the predicted target road segment.Then,the predicted value of LSTM and the collected information of adjacent upstream and downstream sections were simultaneously used as the input features of the random forest model to analyze the spatial-temporal correlation of traffic flow,so as to obtain the final prediction results.The traffic flow data of 132 urban road sections collected by the license plate recognition system in Guiyang City were tested and verified.The results show that the method is better than the single model in prediction accuracy,and the prediction error is obviously reduced compared with the single model.展开更多
The effect of uncertainty about stochastic diffusion model on dynamic portfolio choice of an investor who maximizes utility of terminal portfolio wealth was studied.It applied stochastic control method to obtain the c...The effect of uncertainty about stochastic diffusion model on dynamic portfolio choice of an investor who maximizes utility of terminal portfolio wealth was studied.It applied stochastic control method to obtain the closed-form solution of optimal dynamic portfolio,and used the Bayesian rule to estimate the model parameters to do an empirical study on two different samples of Shanghai Exchange Composite Index.Results show,model uncertainty results in positive or negative hedging demand of portfolio,which depends on investor's attitude toward risk;the effect of model uncertainty is more significant with the increasing of investment horizon,the decreasing of investor's risk-aversion degree,and the decreasing of information;predictability of risky asset return increases its allocation in portfolio,at the same time,the effect of model uncertainty also strengthens.展开更多
We address the question of how the structure condition is affected when one possesses some additional information at the very beginning of the investment period.The structure condition represents essentially an altern...We address the question of how the structure condition is affected when one possesses some additional information at the very beginning of the investment period.The structure condition represents essentially an alternative to non-arbitrage conditions for the Markowitz’s portfolio optimization framework,and is crucial for the existence of the optimal portfolio in quadratic utility settings.Herein,we provide practical assumption on the initial market model and the additional information to preserve the structure condition.The stochastic tools that drive this result are a generalization of the Lazaro-Yor representation by Lazaro and Yor(1978)and optional stochastic integral.展开更多
文摘Traffic flow prediction,as the basis of signal coordination and travel time prediction,has become a research point in the field of transportation.For traffic flow prediction,researchers have proposed a variety of methods,but most of these methods only use the time domain information of traffic flow data to predict the traffic flow,ignoring the impact of spatial correlation on the prediction of target road segment flow,which leads to poor prediction accuracy.In this paper,a traffic flow prediction model called as long short time memory and random forest(LSTM-RF)was proposed based on the combination model.In the process of traffic flow prediction,the long short time memory(LSTM)model was used to extract the time sequence features of the predicted target road segment.Then,the predicted value of LSTM and the collected information of adjacent upstream and downstream sections were simultaneously used as the input features of the random forest model to analyze the spatial-temporal correlation of traffic flow,so as to obtain the final prediction results.The traffic flow data of 132 urban road sections collected by the license plate recognition system in Guiyang City were tested and verified.The results show that the method is better than the single model in prediction accuracy,and the prediction error is obviously reduced compared with the single model.
基金Key program of Natural Science Research of High Education of Anhui Province of China(No.KJ2009A157)
文摘The effect of uncertainty about stochastic diffusion model on dynamic portfolio choice of an investor who maximizes utility of terminal portfolio wealth was studied.It applied stochastic control method to obtain the closed-form solution of optimal dynamic portfolio,and used the Bayesian rule to estimate the model parameters to do an empirical study on two different samples of Shanghai Exchange Composite Index.Results show,model uncertainty results in positive or negative hedging demand of portfolio,which depends on investor's attitude toward risk;the effect of model uncertainty is more significant with the increasing of investment horizon,the decreasing of investor's risk-aversion degree,and the decreasing of information;predictability of risky asset return increases its allocation in portfolio,at the same time,the effect of model uncertainty also strengthens.
基金supported by the Natural Sciences and Engineering Research Council of Canada (Grant No. G121210818)National Natural Science Foundation of China (Grant No. 11501105)
文摘We address the question of how the structure condition is affected when one possesses some additional information at the very beginning of the investment period.The structure condition represents essentially an alternative to non-arbitrage conditions for the Markowitz’s portfolio optimization framework,and is crucial for the existence of the optimal portfolio in quadratic utility settings.Herein,we provide practical assumption on the initial market model and the additional information to preserve the structure condition.The stochastic tools that drive this result are a generalization of the Lazaro-Yor representation by Lazaro and Yor(1978)and optional stochastic integral.
