The research paper ‘Improving the Accuracy of Freight Mode Choice Models’ by Diyi Liu et al. investigates the use of the 2017 Commodity Flow Survey data to develop a high-performance freight mode choice model. The model considers three main improvements: constructing local models for each commodity/industry category, extracting useful geographical features, and applying ensemble learning methods. The proposed method achieved over 92% accuracy without external information, a 19% increase compared to directly fitting Random Forests models over 10,000 samples. The model framework could enhance the performance and interpretability of existing freight mode choice models.
Publication date: 2 Feb 2024
Project Page: ?
Paper: https://arxiv.org/pdf/2402.00654
