A. Turnip, A.N.Q. Aina, Sumarmi, A. Dirpan, Suhaeni, Y. Deliana
This study compares the performance of four machine learning algorithms K-Nearest Neighbor (KNN), Naive Bayes, Decision Tree, and Random Forest in classifying community support for eco-friendly packaging among Millennials. The research addresses Indonesia’s waste management challenges, emphasizing the need for eco-friendly packaging. A 3-class dataset with 795 records and 13 features is analyzed, incorporating pre-processing techniques like Synthetic Minority Oversampling Technique and Principal Component Analysis. Random Forest consistently outperformed the other models, achieving 90.73% accuracy, 91.65% precision, 91.13% recall, and 90.43% F1 score in the 3-class configuration. Decision Tree achieved 86.52% accuracy, while KNN reached 82.02%. Naive Bayes had the lowest performance, with an accuracy of 76.97%. These results provide insights into machine learning applications for optimizing sustainable packaging strategies, aiding businesses and policymakers in promoting eco-friendly packaging solutions. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2025.
Departement of Electrical Engineering, Universitas Padjadaran, Bandung, Indonesia; Department of Geography, Universitas Negeri Malang, Malang, 65145, Indonesia; Department of Agricultural Technology, Universitas Hasanuddin, Makassar, 90245, Indonesia; Department of Agribusiness, Universitas Singaperbangsa Karawang, Karawang, 41361, Indonesia; Agribusiness Department, Faculty of Agriculture, Padjadjaran University, Bandung, Indonesia
Research at a Glance
Register to unlock
Topics & SDG Alignment
Register to unlock
Collaboration
Register to unlock
Author Profile (Selected)
Register to unlock
References Overview
Register to unlock
Journal & Source
Register to unlock
Metadata & Integrity
Register to unlock