Academic Journal of Computing & Information Science, 2024, 7(2); doi: 10.25236/AJCIS.2024.070215.
Feifei Xie1, Wei Yu2
1School of Business, Anhui University, Hefei, 230601, China
2School of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang, 212013, China
Predicting logistics costs is imperative for enterprises to effectively manage and make informed decisions regarding logistics expenditures. This paper employs a systematic approach to this end. Initially, a Pearson correlation analysis is conducted on variables including Line Item Quantity, Line Item Value, Weight, and Freight Cost, revealing a strong correlation between Weight and Freight Cost. Subsequently, a chi-square test is applied to variables such as Fulfill Via, Vendor INCO Term, Shipment Mode, Product Group, Sub Classification, and Freight Cost. This analysis identifies Vendor INCO Term, Shipment Mode, and Sub Classification as pivotal influencing factors. To further enhance predictive accuracy, K Nearest Neighbour Regression (KNN), Support Vector Regression (SVR), and Random Forest (RF) models are individually employed for logistics cost prediction. Comparative analysis of prediction errors indicates that the RF model outperforms KNN, SVR, and other models, showcasing superior logistics cost prediction accuracy.
Logistics Costs, Random Forest, Chi-square Test, Support Vactor Regression, K-Nearest Neighbor
Feifei Xie, Wei Yu. Logistics Cost Prediction Based on Random Forest Model. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 2: 109-114. https://doi.org/10.25236/AJCIS.2024.070215.
[1] SUN Shusheng, LUO Baohua. Application of multiple linear regression model in logistics cost prediction [J]. Business Age, 2014(18):19-21.
[2] CHEN Longtao, LU Shichang,TAI Xiaohong et al. Research on coal logistics cost prediction based on principal component regression analysis [J]. Resource Development and Markets,2015,31(06):641-644.
[3] YANG Jing,LI Junfu, ZHANG Gaoqing. Coal logistics cost prediction based on improved support vector regression machine [J]. Journal of Guangxi University (Natural Science Edition), 2017, 42(04): 1623-1627.
[4] Tong LL. Cross-border e-commerce logistics cost prediction based on neural network [J]. Logistics Technology, 2023, 46(04):48-51.
[5] Su Yuteng, Lv Siyun, Xie Wenhan et al. Analysis of risk factors for the development of type 2 diabetes mellitus based on LASSO regression and random forest algorithm [J]. Journal of Environmental Hygiene, 2023, 13(07): 485-495.
[6] LIU Fuqiang, CHEN Xiaodong, LI Shengfu et al. Prediction of permeability coefficient of sand body based on random forest regression [J]. Uranium Ore Geology, 2023, 39(04): 653-661.
[7] Ding Sha; Shen Taorong; Zhang Yanfei; Du Huanzhe; Wu Yu; Zou Xiaoyong. A study on category identification model of tobacco extracts based on random forest algorithm [J]. Journal of Analytical Testing, 2023, 42(11):1510-1516.
[8] Zou, Jie; Li, Lu. A study on stock price prediction based on SA-BiGRU model with random forests [J]. Commodity Prices in China, 2023, (11):52-56.
[9] GUO Liang, GUO Zixue, JIA Hongtao et al. Identification of residential electricity theft based on Pearson correlation coefficient and SVM [J]. Journal of Hebei University (Natural Science Edition), 2023, 43(04):357-363.