Semantic Scholar Open Access 2025

Leveraging Machine Learning and Data Mining Techniques for Predictive Analytics in Supply Chain Logistics Management

Qianxi Kong

Abstrak

In the context of machine learning, this study investigates the efficacy of different learning methods in analyzing big data in supply chain and accuracy of predicting logistics late delivery, while exploring impacts of hyperparameters tuning on different model evaluation metrics. The research employed comprehensive variables such as destination, timestamps, and quantity of goods, and evaluated them comprehensively based on multiple indicators including accuracy, recall and precision. The Decision Tree Classifier model after parameter tuning displays the best performance, achieving a 0.7081 test accuracy, as well as a precision score of 0.7601 and recall score of 0.7081, indicating a relatively balanced overall performance. The variable ‘Days for shipment (scheduled)’ comes up as the variable with the highest contribution ranking for predicting, importance doing 0.6840. This study provides a substantial data support for supply chain risk warning system, which is conducive to reduction of logistics waste and raising operational efficiency in supply chain networks.

Penulis (1)

Q

Qianxi Kong

Format Sitasi

Kong, Q. (2025). Leveraging Machine Learning and Data Mining Techniques for Predictive Analytics in Supply Chain Logistics Management. https://doi.org/10.1145/3766671.3766814

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1145/3766671.3766814
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
Semantic Scholar
DOI
10.1145/3766671.3766814
Akses
Open Access ✓