Research on product price forecasting method based on fusion model
Product price forecasting is beneficial to product manufacturers to avoid risks and adjust production decisions,so it is necessary to do price forecasting in the production field.In order to improve the accuracy of price prediction,the random forest model,ridge regression model and extreme gradient lifting model are organically integrated by Adaboost al-gorithm,and a fusion model of price prediction is constructed.The model weights the forecast results of three single models to get a more accurate forecast.The experimental results show that the model can truly reflect the changing trend of product price,and its R2 value is 0.998,indicating that the model has a good fit.The root-mean-square error and mean absolute error of this model are 94.968 and 44.2,respectively,which are smaller than other comparison models.It can be seen that the model synthesizes the advantages of a single model,and the prediction error of product price is small,which can predict product price more accurately,and can provide theoretical support for the product reproduction decision of enterprises.
NETL
NSTL
万方数据
