:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that i...:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that improves the prediction of next day closing prices.In the proposed model we use multiple neural networks where the first one uses the closing stock prices from multiple-scale time-domain inputs.An additional network is used for error estimation to compensate and reduce the prediction error of the main network instead of using recurrence.The performance of the proposed model is evaluated using six different stock data samples in the New York stock exchange.The results have demonstrated significant improvement in forecasting accuracy in all cases when the second network is used in accordance with the first one by adding the outputs.The RMSE error is 33%improved when the proposed PEC-WNN model is used compared to the Long ShortTerm Memory(LSTM)model.Furthermore,through the analysis of training mechanisms,we found that using the updated training the performance of the proposed model is improved.The contribution of this study is the applicability of simultaneously different time frames as inputs.Cascading the predictive error compensation not only reduces the error rate but also helps in avoiding overfitting problems.展开更多
Investors should always argue about management fees because of their impact on net performance that can be substantial.This especially for investments,like real estate,which require intensive management.However,differ...Investors should always argue about management fees because of their impact on net performance that can be substantial.This especially for investments,like real estate,which require intensive management.However,different from traditional mutual funds that are usually related to the gross value of the assets under management,but similar to other financial industry sectors(e.g.hedge funds and private equity funds),REIT managers’compensation structure typically provides a basically fixed payment based alternatively on gross asset value(GAV)or net asset value(NAV).In addition,managers usually also gain a performance fee.The paper analyses how the two alternative compensation schemes influence REITs’investment decisions and capital structure and,consequently,REITs’share value and performance.The final issue addressed is whether—and under which conditions—one compensation scheme is superior to the other.Due to the(usual)market price discount on NAVs,both fee structures incentivise managers to leverage—even in a tax-free environment—in order to maximize the management fees.However,the leverage motivation is stronger for GAV-based than for NAV-based REITs,which are also expected to be more selective in investment decisions.Overall,considering initial fee percentage,GAV-based REITs are expected to execute higher management fees than NAV-based REITs due to the relevant leverage effect.Moreover,debt recourse produces different effects on share value if measured upon market price or net asset value.The empirical analysis focuses on public Italian REITs(2002-2012).The results seem to support the theoretical expectations.GAV-based REITs experience higher debt trends and levels than NAV-based REITs.At the same time,GAV-based REITs register lower real estate asset returns gross and net of management fees for both current and growth yields.Differences in the returns lead to permanent higher performances over total return indexes of NAV-based REITs compared to GAV-based REITs.展开更多
随着电动汽车(electric vehicle,EV)普及度的不断提高,工业园区内的EV用户日益增多,其充放电行为给园区综合能源系统(park integrated energy system,PIES)的规划运行带来极大挑战。文中提出考虑EV充放电意愿的PIES双层优化调度。首先,...随着电动汽车(electric vehicle,EV)普及度的不断提高,工业园区内的EV用户日益增多,其充放电行为给园区综合能源系统(park integrated energy system,PIES)的规划运行带来极大挑战。文中提出考虑EV充放电意愿的PIES双层优化调度。首先,基于动态实时电价、电池荷电量、电池损耗补偿、额外参与激励等因素建立充放电意愿模型,在此基础上得到改进的EV充放电模型;然后,以PIES总成本最小和EV充电费用最小为目标建立双层优化调度模型,通过Karush-Kuhn-Tucker(KKT)条件将内层模型转化为外层模型的约束条件,从而快速稳定地实现单层模型的求解;最后,进行仿真求解,设置3种不同场景,对比所提模型与一般充放电意愿模型,验证了文中所提引入EV充放电意愿模型的PIES双层优化调度的有效性和可行性。展开更多
基金This study is based on the research project“Development of Cyberdroid based on Cognitive Intelligent system applications”(2019–2020)funded by Crypttech company(https://www.crypttech.com/en/)within the contract by ITUNOVA,Istanbul Technical University Technology Transfer Office.
文摘:Machine Learning(ML)algorithms have been widely used for financial time series prediction and trading through bots.In this work,we propose a Predictive Error Compensated Wavelet Neural Network(PEC-WNN)ML model that improves the prediction of next day closing prices.In the proposed model we use multiple neural networks where the first one uses the closing stock prices from multiple-scale time-domain inputs.An additional network is used for error estimation to compensate and reduce the prediction error of the main network instead of using recurrence.The performance of the proposed model is evaluated using six different stock data samples in the New York stock exchange.The results have demonstrated significant improvement in forecasting accuracy in all cases when the second network is used in accordance with the first one by adding the outputs.The RMSE error is 33%improved when the proposed PEC-WNN model is used compared to the Long ShortTerm Memory(LSTM)model.Furthermore,through the analysis of training mechanisms,we found that using the updated training the performance of the proposed model is improved.The contribution of this study is the applicability of simultaneously different time frames as inputs.Cascading the predictive error compensation not only reduces the error rate but also helps in avoiding overfitting problems.
文摘Investors should always argue about management fees because of their impact on net performance that can be substantial.This especially for investments,like real estate,which require intensive management.However,different from traditional mutual funds that are usually related to the gross value of the assets under management,but similar to other financial industry sectors(e.g.hedge funds and private equity funds),REIT managers’compensation structure typically provides a basically fixed payment based alternatively on gross asset value(GAV)or net asset value(NAV).In addition,managers usually also gain a performance fee.The paper analyses how the two alternative compensation schemes influence REITs’investment decisions and capital structure and,consequently,REITs’share value and performance.The final issue addressed is whether—and under which conditions—one compensation scheme is superior to the other.Due to the(usual)market price discount on NAVs,both fee structures incentivise managers to leverage—even in a tax-free environment—in order to maximize the management fees.However,the leverage motivation is stronger for GAV-based than for NAV-based REITs,which are also expected to be more selective in investment decisions.Overall,considering initial fee percentage,GAV-based REITs are expected to execute higher management fees than NAV-based REITs due to the relevant leverage effect.Moreover,debt recourse produces different effects on share value if measured upon market price or net asset value.The empirical analysis focuses on public Italian REITs(2002-2012).The results seem to support the theoretical expectations.GAV-based REITs experience higher debt trends and levels than NAV-based REITs.At the same time,GAV-based REITs register lower real estate asset returns gross and net of management fees for both current and growth yields.Differences in the returns lead to permanent higher performances over total return indexes of NAV-based REITs compared to GAV-based REITs.
文摘随着电动汽车(electric vehicle,EV)普及度的不断提高,工业园区内的EV用户日益增多,其充放电行为给园区综合能源系统(park integrated energy system,PIES)的规划运行带来极大挑战。文中提出考虑EV充放电意愿的PIES双层优化调度。首先,基于动态实时电价、电池荷电量、电池损耗补偿、额外参与激励等因素建立充放电意愿模型,在此基础上得到改进的EV充放电模型;然后,以PIES总成本最小和EV充电费用最小为目标建立双层优化调度模型,通过Karush-Kuhn-Tucker(KKT)条件将内层模型转化为外层模型的约束条件,从而快速稳定地实现单层模型的求解;最后,进行仿真求解,设置3种不同场景,对比所提模型与一般充放电意愿模型,验证了文中所提引入EV充放电意愿模型的PIES双层优化调度的有效性和可行性。
