时间序列预测
3、Prophet
官方文档:https://facebook.github.io/prophet/docs/quick_start.html#python-api
文档简译:https://www.jianshu.com/p/68298c3d0dc0
paper: https://peerj.com/preprints/3190.pdf
2、时间序列分析的AR/MA/ARMA/ARIMA模型体系
AR/MA/ARMA : 平稳序列
ARIMA : 非平稳序列 (差分后是平稳序列)
这四种模型的名称都是它们英文全称的缩写。AR模型称为自回归模型(Auto Regressive model);MA模型称为移动平均模型(Moving Average model);ARMA称为自回归移动平均模型(Auto Regressive and Moving Average model);ARIMA模型称为差分自回归移动平均模型(Auto Regressive Integrated Moving Average model)
1、LSTM
Time Series Prediction with LSTM Recurrent Neural Networks in Python with Keras