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

نویسندگان

چکیده

The choice of vehicle type is one the important logistics decisions made by firms. complex nature process because involvement multiple agents. This study employs a random forest machine learning algorithm to represent these interactions with limited information about shipment transportation. data are from Commercial Travel Surveys outbound models among four road transport types: pickup/cube van, single-unit truck, tractor trailer, and passenger car. characteristics firms shipments used as explanatory variables. SHAP-based variable importance calculated interpret each variable, shows that employment weight most variables in determining type. model also compared multinomial mixed logit models. prediction results on validation compared. show outperforms both an overall increase accuracy 7.8% 9.6%, respectively.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Discrete Choice Modeling

Do the results change substantially when the restriction is imposed? Does the estimate of ρ change? The hypothesis of interest is H0: β1 = β2. You can test this hypothesis using these models with a likelihood ratio test. Compute twice the difference in the log likelihoods. What are the degrees of freedom for the test? What is the 95% critical value from the chi squared table? (It is also possib...

متن کامل

Designing social choice mechanisms using machine learning

Social choice studies ordinal preference and information aggregation with applications in high-stakes political elections as well as low-stakes movie rating websites. Recently, computational aspects of classical social choice mechanisms have been extensively investigated, yet not much has been done in designing new mechanisms with the help of computational techniques. In this paper, we outline ...

متن کامل

Discrete Choice Modeling for Transportation

Acknowledgements: Justin Tobias provided many useful references and comments on the third section of this paper. provided many useful comments and references. Of course, none of these people are responsible for any of the errors or omissions in this paper.

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Transportation Research Record

سال: 2021

ISSN: ['2169-4052', '0361-1981']

DOI: https://doi.org/10.1177/03611981211044462