Prediction of Arrival Times of Container Transport on Fangchenggang-Yuxi Railroads Using Random Forest Model

Railway container transport time affects logistics delivery, train scheduling, etc. Predicting accurate estimated arrival times (ETAs) is an important step for railways to improve efficiency and enhance customer service. In this paper, a random forest regression model of container ETA with container transport time as the dependent variable was developed using Python language, based on the transport trajectory data of containers on the Fangchenggang-Yuxi railway line and the seven main influencing factors of ETA as the independent variables. The prediction results show that the model can achieve a prediction accuracy of over 95% with an allowable loss of 1.5 h. The comparison of the random forest model with the multiple linear regression model and the support vector machine model shows that the random forest model has the best prediction accuracy. This paper can provide a scientific and theoretical basis for the innovation of the existing transit period calculation methods.