摘要
本文基于美元指数的日频历史数据,首次使用长短期记忆神经网络(Long Short-Term Memory,简记LSTM)模型对美元走势做出预测。同时运用小波变换(Wavelet Transform,简记WT)预处理数据后,与原单时间序列模型进行对比。研究发现,美元指数的LSTM模型能较好拟合,且小波变换进行信号降噪能够提高预测精度。最后本文将模型模拟结果与宏观分析结合,提出了近期美元走势将下行的判断。
Based on the analysis of the far-reaching impact of the integrated development of the Yangtze River Delta,this article interprets the characteristics of cross-organizational technology innovation team,analyzes each link of the team performance management process,and proposes the countermeasures to improve the efficiency of the performance management process of cross-organizational technology innovation team.
作者
陈克标
CHEN Ke-biao(School of Economics&Management,Southeast University,Nanjing 211100,China)
出处
《价值工程》
2020年第15期17-19,共3页
Value Engineering
关键词
小波变换
长短期记忆神经网络
美元指数
integration of the Yangtze River Delta
cross-organizational technology innovation team
performance management
process
