Analysis and Prediction of Steel Prices Based on LSTM Neural Network Model
Steel price time series has obvious long and short memory characteristics.Taking the amount of HRB400Eφ16 rebar actually purchased by the project department of a construction enterprise in Anhui Province as an example,the LSTM model is scientifically and reasonably used to model it,and compared with the traditional ARIMA model,the results show that the relative error of the prediction of the LSTM model is 0.03.It is more accurate than ARIMA model and suitable for predicting construction steel prices.
prediction of steel pricestime seriesLSTM modelARIMA modellong and short-term memory
NETL
NSTL
万方数据
