Year: 2024
Type: conference-paper
Abstract: With the rapid development of globalization, container cargo transportation occupies a core position in international trade, but the loss and damage of its goods have brought huge economic losses and reputation risks to both sides of the trade. To meet this challenge, this paper proposes a fusion model combining Random Forest (RF) and Gradient Boosting Decision Tree (GBDT) to predict the risk of loss and damage of container goods during transportation. Firstly, through collecting about 15,000 cargo transportation records of a company in the last three years, covering multi-dimensional data such as cargo attributes, transportation environment and whether it is lost or damaged, and cleaning and preprocessing the data. Subsequently, an integrated learning model based on RF and GBDT is constructed, and the model is trained and optimized by cross-validation and feature selection methods. The experimental results show that the fusion model is superior to the single RF and GBDT models in accuracy, precision, recall, and F1 score, with an accuracy of about 90%, which shows high prediction accuracy and robustness. The research in this paper not only verifies the effectiveness of machine learning in the risk prediction of container cargo loss and damage but also puts forward a strategy to improve prediction accuracy through model fusion. In addition, according to the experimental results and the analysis of the importance of characteristics, this paper puts forward a series of measures to reduce the risk of goods transportation, such as strengthening the classification of goods and customizing protection measures, monitoring key environmental factors, optimizing transportation routes, etc., which provides scientific basis and practical suggestions for the risk management of goods transportation industry.
Author: Nong Ting
Institution: Wuhan Railway Vocational College of Technology
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4412524706