Modeling Freight Vehicle Type Choice using Machine Learning and Discrete Choice Methods

Ahmed, Usman; Roorda, Matthew J.

doi:10.1177/03611981211044462

Cited by 13 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers Ahmed U. and Roorda M.J. used machine learning algorithms to forecast the vehicle type choice by the enterprise, depending on the field of activity and the type of cargo delivered. In their paper [15], scientists compared the effectiveness of three models, which are the Random Forest model (RF), the Multinomial Logit Model (MNL), and the Mixed Logit Model (Mixed MNL). Forecasting of vehicle type is carried out based on such variables as a sphere of operation, number of employees, type of cargo, weight, point of departure and destination.…”

Section: Fig1 Stages Of Application Of An Intelligent Approach In Alg...mentioning

confidence: 99%

“…Linear regression models are used to forecast fuel consumption by vehicles [23], while logistic regression models due to their main task (classification) are used to choose the type of vehicle for cargo delivery [15]. retraining [30].…”

Section: Advantages Disadvantages and Areas Of Application Of Algorit...mentioning

confidence: 99%

“…Application of the random forest model for forecasting fuel consumption by freight vehicles showed the highest forecast accuracy compared to other machine learning models [18; 22]. Also, this type of model demonstrates high efficiency indicators when forecasting the choice of the type of vehicle for cargo delivery [15]. In the case of forecasting the duration of cargo delivery, this model did not show sufficiently accurate results [9; 11].…”

Section: Advantages Disadvantages and Areas Of Application Of Algorit...mentioning

confidence: 99%

See 2 more Smart Citations

Application of algorithmic models of machine learning to the freight transportation process

Kotenko¹

2022

View full text Add to dashboard Cite

The results of the analysis of algorithmic models of machine learning application to the freight transportation process are given in this paper. Analysis of existing research allowed discovering a range of advantages in the application of computational intelligence in logistic systems, including increasing the accuracy of forecasting, reduction of transport costs, increasing the efficiency of cargo delivery, risks reduction, and search for key performance factors. In the research process, the main directions of application of algorithmic models of machine learning were determined. They are vehicle routing, choice of cargo type, transportation type and vehicle type; forecasting fuel consumption by vehicles, disruptions in transportation, transport costs, duration of the order fulfillment; evaluation of the rolling stock fleet and the efficiency of carrying out the transport task. Based on the researched publications, the most common algorithmic models of machine learning in freight transportation were identified, and their effectiveness was analyzed. Linear and logistic regression models are simple enough; however, they do not always provide high simulation results. Deep learning models are quite widely applied to all identified areas. Decision tree and random forest models often show the highest simulation performance. Models of k-nearest neighbors and support vectors should be used both in classification tasks, for example, in choosing the type of cargo and type of transportation, and for forecasting the fuel consumption and the duration of the transport process.

show abstract

Section: Fig1 Stages Of Application Of An Intelligent Approach In Alg...mentioning

confidence: 99%

Section: Advantages Disadvantages and Areas Of Application Of Algorit...mentioning

confidence: 99%

Section: Advantages Disadvantages and Areas Of Application Of Algorit...mentioning

confidence: 99%

See 1 more Smart Citation

Application of algorithmic models of machine learning to the freight transportation process

Kotenko¹

2022

View full text Add to dashboard Cite

show abstract

“…The choice of vehicle type plays a vital role in logistics decision. Ahmed, U, et al [24] employ the random forest machine learning algorithm to represent the complex interactions in the logistics and transportation process with restricted information about the transportation of goods. The results of the research show that the overall accuracy of the random forest model is improved.…”

Section: Random Forestmentioning

confidence: 99%

A review of the application of machine learning technologies in vehicle navigation and positioning

Zheng

et al. 2022

Second International Conference on Optics and Communication Technology (ICOCT 2022)

View full text Add to dashboard Cite

In recent years, the accuracy requirement of vehicle navigation and positioning is higher and higher. Since some obvious disadvantages emerge in the integration of various traditional technologies, many studies have begun to apply machine learning to vehicle navigation and positioning, which utilize the powerful self-learning ability of machine learning algorithms. The main advantages of machine learning methods include solving the problem of narrow application scope of traditional information fusion algorithms. Solve the problems of low navigation and positioning accuracy and poor anti-interference ability. In this paper, the applications of machine learning related algorithms in vehicle navigation and localization are overviewed in detail, including support vector machines, neural networks and random forests. Meanwhile, the application research status of machine learning technology in vehicle navigation and positioning is summarized, and the future research directions are prospected.

show abstract

“…To date, a handful of studies have adopted the SHAP approach for passenger travel behavior analysis (Zima-Bockarjova et al, 2020;Jin et al, 2022;Lee, 2022). However, its application in understanding freight behavior (Ahmed and Roorda, 2022), especially in freight mode choice, remains limited.…”

Section: Introductionmentioning

confidence: 99%

Teaching freight mode choice models new tricks using interpretable machine learning methods

Xu,

Yang,

Jeong

et al. 2024

Front. Future Transp.

View full text Add to dashboard Cite

Understanding and forecasting complex freight mode choice behavior under various industry, policy, and technology contexts is essential for freight planning and policymaking. Numerous models have been developed to provide insights into freight mode selection; most use discrete choice models such as multinomial logit (MNL) models. However, logit models often rely on linear specifications of independent variables despite potential nonlinear relationships in the data. A common challenge for researchers is the absence of a heuristic and efficient method to discern and define these complex relationships in logit model specifications. This often results in models that might be deficient in both predictive power and interpretability. To bridge this gap, we develop an MNL model for freight mode choice using the insights from machine learning (ML) models. ML models can better capture the nonlinear nature of many decision-making processes, and recent advances in “explainable AI” have greatly improved their interpretability. We showcase how interpretable ML methods help enhance the performance of MNL models and deepen our understanding of freight mode choice. Specifically, we apply SHapley Additive exPlanations (SHAP) to identify influential features and complex relationships to improve the MNL model’s performance. We evaluate this approach through a case study for Austin, Texas, where SHAP results reveal multiple important nonlinear relationships. Incorporating those relationships into MNL model specifications improves the interpretability and accuracy of the MNL model. Findings from this study can be used to guide freight planning and inform policymakers about how key factors affect freight decision-making.

show abstract

Modeling Freight Vehicle Type Choice using Machine Learning and Discrete Choice Methods

Cited by 13 publications

References 37 publications

Application of algorithmic models of machine learning to the freight transportation process

Application of algorithmic models of machine learning to the freight transportation process

A review of the application of machine learning technologies in vehicle navigation and positioning

Teaching freight mode choice models new tricks using interpretable machine learning methods

Contact Info

Product

Resources

About