A Comparison between Different Data Mining Algorithms in Freight Mode Choice

Abstract

This research aims to study application of support vector machine algorithm, artificial neural networks and five different types of decision trees in predicting mode choice of freight transportation. Performance of these models has been compared with log it model which is one the most prevalent statistical models in the field. Effect of factors such as cargo weight, distance, type and characteristics of commodity has been studied in process of modelling mode choice which is rail and road. In this regard, data gathered in the United States, is used and similarities and advantages of the models are described in details. Results indicated that cost-sensitive support vector machine is the best method in predicting shipment mode choice. After this method, stand C5 decision tree and artificial neural network. The most important variables in determining shipment mode choice of firms are respectively weight, great-circle distance between origin and destination, commodity type, compound impedance factor of rail and truck and containerized condition of the shipment to be moved.