Packaging Planning Prediction Using Multi-Class and Multi-Output Algorithms

Abstract

In the rapidly evolving industrial landscape, Artificial Intelligence (AI) has emerged as a transformative force in various sectors, including manufacturing and supply chain management. Meanwhile, packaging planning is another area that is still open to development for AI. Effective packaging planning is a complicated task to be handled carefully throughout the entire planning process. To solve this problem, we propose a relation-based heterogeneous chain-based multi-output classification model for effective packaging planning in predicting the dimensions and types of packages for each shipment. While conventional regressor chain models typically employ only a single classifier within each chain, our model allows for the utilization of distinct classifiers within each chain. Our model is analyzed on a real-world dataset by employing different multi-output classification algorithms including Random Forest (RF), Decision Trees (DT), and K-Nearest Neighbors (KNN). Experimental results demonstrate that our homogeneous chain-based multi-output classification model, based solely on a DT, and our relation-based heterogeneous chain-based multi-output classification model outperform others, achieving the highest accuracy with an overall accuracy value of 0.98, as compared to traditional multi-output classification and chain regression models. Additionally, our heterogeneous chain-based multi-output classification model, utilizing different classifiers, has the second-highest overall accuracy result among all models and surpasses the overall accuracy achieved by traditional chain-based models.