Summary of Improving the Accuracy Of Freight Mode Choice Models: a Case Study Using the 2017 Cfs Puf Data Set and Ensemble Learning Techniques, by Diyi Liu et al.
Improving the accuracy of freight mode choice models: A case study using the 2017 CFS PUF data set and ensemble learning techniques
by Diyi Liu, Hyeonsup Lim, Majbah Uddin, Yuandong Liu, Lee D. Han, Ho-ling Hwang, Shih-Miao Chin
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study proposes a high-performance freight mode choice model using data from the 2017 Commodity Flow Survey Public Use File. By constructing local models for each commodity/industry category, extracting geographical features like distance between origin/destination zones, and applying ensemble learning methods, the model achieves over 92% accuracy without external information. This is a significant improvement of 19% compared to directly fitting Random Forests models. The study also uses SHAP values to explain the outputs and major patterns obtained from the proposed model. The framework could enhance existing freight mode choice models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper builds a better freight mode choice model using data from a survey. It makes three changes: it creates separate models for different types of goods, adds information about how far apart places are, and combines results from different models to make it more accurate. This helps the model be correct over 92% of the time without extra help. The study also uses SHAP values to understand why the model makes certain choices. |
