In order to improve the prediction accuracy and modeling speed of railway freight volume, this paper combines the cargo floating price prediction model with the neural network algorithm (hereinafter referred to as NNA) to establish a prediction model. The railway cargo floating price based on neural network (hereinafter referred to as PMBCFP) relies on the random forest regression algorithm (hereinafter referred to as RFRA). Through the neural network operator in the prediction model of the floating price of goods, the randomness of the original sequence is weakened, and the implicit rules in the series are mined. The characteristics of neural networks are computationally very simple. In addition, a random forest regression algorithm is applied to the optimization, RFRA’s choice. Case studies of China’s rail freight volume show that RMSE and other indicators are faster. The MAE, MPE and Tell inequality coefficients obtained from this model were 0.0628, 0.0523, 0.0162 and 0.0107, respectively. This model has good prediction results. The time to search for the best parameters of RFRA using the NNA algorithm is 55.656 s, which is 10.462 s less than the time required for traditional cross-validation methods. Therefore, it is suitable for short-term forecasting of railway freight volume.
Prediction of the volume of railway freight Prediction model of cargo floating price Neural network Random forest regression algorithm
This is a preview of subscription content, log in to check access.
This work was supported by the National Natural Science Foundation of China (No. 61803147), the Key Scientific and Technological Project of Henan Province (No. 182102310799) and the Foundation of Henan Educational Committee (No. 18A580003).
Compliance with ethical standards
Conflict of interest
There are no conflicts of interest.
Grote M, Mazurek N, Gräbsch C, Zeilinger J, Le FS, Wahrendorf DS (2016) Dry bulk cargo shipping—an overlooked threat to the marine environment? Mar Pollut Bull 110(1):511–519CrossRefGoogle Scholar
Scholten A, Rothstein B, Baumhauer R (2014) Mass-cargo-affine industries and climate change: the vulnerability of bulk cargo companies along the river Rhine to low water periods. Clim Change 122:111–125CrossRefGoogle Scholar
Ju L, Vassalos D, Wang Q, Wang Y, Liu Y (2018) Numerical investigation of solid bulk cargo liquefaction. Ocean Eng 159:333–347CrossRefGoogle Scholar
Dondo RG, Mendez CA (2014) A branch-and-price approach to manage cargo consolidation and distribution in supply chains. Ind Eng Chem Res 53(44):17226–17239CrossRefGoogle Scholar
Bitzan JD, Keeler TE (2014) The evolution of u.s. rail freight pricing in the post-deregulation era: revenues versus marginal costs for five commodity types. Transportation 41(2):305–324CrossRefGoogle Scholar
Bababeik M, Nasiri MM, Khademi N, Chen A (2017) Vulnerability evaluation of freight railway networks using a heuristic routing and scheduling optimization model. Transportation(3):1–28Google Scholar
Fügenschuh A, Homfeld H, Schülldorf H (2015) Single-car routing in rail freight transport. Transp Sci 49(1):130–148CrossRefGoogle Scholar
Feo-Valero M, García-Menéndez L, Saz-Salazar SD (2016) Rail freight transport and demand requirements: an analysis of attribute cut-offs through a stated preference experiment. Transportation 43(1):101–122CrossRefGoogle Scholar
Naweed A, Balakrishnan G, Dorrian J (2018) Going solo: hierarchical task analysis of the second driver in “two-up” (multi-person) freight rail operations. Appl Ergon 70:202–231CrossRefGoogle Scholar
Vakkalagadda MRK, Vineesh KP, Racherla V (2015) Estimation of railway wheel running temperatures using a hybrid approach. Wear 328–329:537–551CrossRefGoogle Scholar
Zeng XH, Wu H, Lai J, Sheng HZ (2014) Influences of aerodynamic loads on hunting stability of high-velocity railway vehicles and parameter studies. Acta Mech Sin 30(6):889–900MathSciNetCrossRefGoogle Scholar
Kwon H, Lyu B, Tak K, Lee J, Cho JH, Moon I (2016) Optimization of naphtha purchase price using a price prediction model. Comput Chem Eng 84(1):226–236CrossRefGoogle Scholar
Xie Z (2015) Case vii on the prediction of freight transportation by a new model fitting procedure of time series. J Approx Theory 2(4):448–449Google Scholar
Zhang W, Li C, Ye Y, Li W, Ngai EWT (2015) Dynamic business network analysis for correlated stock price movement prediction. IEEE Intell Syst 30(2):26–33CrossRefGoogle Scholar
Chang TY, Lin HC, Yang WT, Bao BY, Chan CC (2012) A modified Nordic prediction model of road traffic noise in a Taiwanese city with significant motorcycle traffic. Sci Total Environ 432(432):375–381CrossRefGoogle Scholar
Fallah A, Fallah A, Fallah A, Pelz D (2012) Forest attribute imputation using machine-learning methods and aster data: comparison of k-NN, SVR and random forest regression algorithms. Int J Remote Sens 33(19):6254–6280CrossRefGoogle Scholar
Rodriguez-Galiano V, Sanchez-Castillo M, Chica-Olmo M, Chica-Rivas M (2015) Machine learning predictive models for mineral perspectivity: an evaluation of neural networks, random forest, regression trees and support vector machines. Ore Geol Rev 71:804–818CrossRefGoogle Scholar
Peters HJF (2001) Developments in global seatrade and container shipping markets: their effects on the port industry and private sector involvement. Int J Marit Econ 3(1):3–26CrossRefGoogle Scholar
Caves DW, Christensen LR (1980) The relative efficiency of public and private firms in a competitive environment: the case of Canadian railroads. J Polit Econ 88(5):958–976CrossRefGoogle Scholar
Christiansen M, Fagerholt K, Ronen D (2004) Ship routing and scheduling: status and perspectives. Transp Sci 38(1):1–18CrossRefGoogle Scholar
Rich J, Holmblad PM, Hansen CO (2009) A weighted logit freight mode-choice model. Transp Res E Logist Transp Rev 45(6):1006–1019CrossRefGoogle Scholar