Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically ...Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual involvement.This manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series models.The complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple junctures.To surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series prediction.However,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series tasks.Therefore,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time series.ARIMA is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing efforts.Using multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long term.Furthermore,our findings indicate its superiority over alternative network architectures,including Fully Connected Neural Networks,Convolutional Neural Networks,and Nonpooling Convolutional Neural Networks.Our AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.展开更多
Big data analytics(BDA)in e-commerce,which is an emerging field that started in 2006,deeply affects the development of global e-commerce,especially its layout and performance in the U.S.and China.This paper seeks to e...Big data analytics(BDA)in e-commerce,which is an emerging field that started in 2006,deeply affects the development of global e-commerce,especially its layout and performance in the U.S.and China.This paper seeks to examine the relative influence of theoretical research of BDA in e-commerce to explain the differences between the U.S.and China by adopting a statistical analysis method on the basis of samples collected from two main literature databases,Web of Science and CNKI,aimed at the U.S.and China.The results of this study help clarify doubts regarding the development of China's e-commerce,which exceeds that of the U.S.today,in view of the theoretical comparison of BDA in e-commerce between them.展开更多
文摘Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual involvement.This manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series models.The complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple junctures.To surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series prediction.However,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series tasks.Therefore,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time series.ARIMA is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing efforts.Using multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long term.Furthermore,our findings indicate its superiority over alternative network architectures,including Fully Connected Neural Networks,Convolutional Neural Networks,and Nonpooling Convolutional Neural Networks.Our AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.
基金Supported by the Ministry of Education’s Humanities and Social Sciences Research Project(18YJAZH153)Fujian Natural Science Foundation(2018J01648)+1 种基金Fujian Social Sciences Federation Planning Project(FJ2018B032)Development Fund of Scientific Research from Fujian University of Technology(GY-S18109)。
文摘Big data analytics(BDA)in e-commerce,which is an emerging field that started in 2006,deeply affects the development of global e-commerce,especially its layout and performance in the U.S.and China.This paper seeks to examine the relative influence of theoretical research of BDA in e-commerce to explain the differences between the U.S.and China by adopting a statistical analysis method on the basis of samples collected from two main literature databases,Web of Science and CNKI,aimed at the U.S.and China.The results of this study help clarify doubts regarding the development of China's e-commerce,which exceeds that of the U.S.today,in view of the theoretical comparison of BDA in e-commerce between them.