Table 1

Summary of some of the methods reviewed

ResearchMethodDatasetEvaluation
Servos et al. (2019) Support Vector Regression (SVR)Real-world multi-dimensional container transportation relationship from Germany to the United StatesPrediction accuracy with a mean absolute error of 17 h for delivery time up to 30 days
Erkmen et al. (2022) Support Vector Machine (SVM)Sample dataset obtained from KaggleMean MAE achieved with the backward-looking approach (3.81)
Mahajan et al. (2022) Multiple Regression TechniquesInternal data on shipments stored by a company, and secondly, maritime traffic data89% accuracy
Kandula et al. (2021) Decision Support FrameworkTwo real-world datasets from a major e-commerce platform10.2% savings in delivery costs
Bani-Mustafa et al. (2018) Fixed and Random Multivariate Regression ModelThree years of data from Elghanem Desert transportation (2014–2016)Detection of 38.7% of all changes in delivery time
Alnahhal et al. (2021) Linear Regression and Logistic RegressionReal data from a logistics companyType 1 error with an average value of 0.07
Barros et al. (2023) Random Forest ModelEmpirical data from a large automobile manufacturerAverage reduction of 18%–24% in mean absolute errors
Pineda-Jaramillo et al. (2023) Tuned LightGBMdata from the Luxembourg National Railway Companyaccuracy of 93.8%
Al-Saghir (2022) Logistic RegressionDataco supply chain dataset from Kaggleaccuracy of 75.13%
Shi et al. (2021) combining eXtreme Gradient Boosting (XGBoost) and Bayesian optimization (BOtwo high-speed railway lines in ChinaRMSE of 2.686/1.887
Source(s): The authors

or Create an Account

Close Modal
Close Modal