The forecast of railway freight volume has important influence on effective allocation of railway resource. In the paper, we introduced a novel non-linear regression method: random forest regression (RFR), to quantitatively estimate China railway freight volume. Through analyzing the monthly data on railway freight volume between 2001 and 2013 by RFR model, we get a series of predicted results and the results show that Mean Absolute Error and Mean Relative Error are respectively 736.15 million tons and 3.32%. The RFR model has the characteristics of high precision of prediction, strong generalization ability, good robust performance and less adjustable parameters.
Forecast of China railway freight volume by random forest regression model
2015-07-01
320314 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Random Forest Regression Model Application for Prediction of China’s Railway Freight Volume
Springer Verlag | 2021
|Railway Freight Volume Forecast Based on GRA-WD-WNN
IEEE | 2019
|Railway freight volume forecast using an ensemble model with optimised deep belief network
Wiley | 2018
|Railway freight volume forecast using an ensemble model with optimised deep belief network
IET | 2018
|