Abstract
Food packaging is critical for ensuring food safety, quality, and shelf life. However, growing environmental concerns with conventional plastics drive the search for sustainable alternatives. A major challenge is that many biobased and biodegradable materials show poor barrier properties, limiting their use for food. This study provides a proof-of-concept for classifying sustainable packaging materials by clustering oxygen transmission rate (OTR) and water vapor transmission rate (WVTR) data. A dataset from 49 studies (2000 to 2016) was analyzed using K-Means, Gaussian Mixture Model (GMM), and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). DBSCAN emerged as best performing algorithm, achieving the highest Silhouette Score (0.910) and lowest Davies-Bouldin Index (0.374). Results validated that while many sustainable films exhibit high permeability, nanocomposites achieved improved barrier performance. This data-driven framework demonstrates clustering as a tool for systematic grouping of packaging materials, with future work requiring broader datasets, industrial benchmarks, and standardized reporting for practical application.