Sustainability assessment and modeling based on supervised machine learning techniques: The case for food consumption

摘要: Abstract Sustainability of food consumption requires the understanding multi-dimensional environmental, economic and social impacts using a holistic integrated sustainability assessment modeling framework. This article presents novel method on consumption. First, categories are quantified high sector resolution input-output tables U.S. economy. Later, an framework based two supervised machine-learning techniques such as k-means clustering logistics regression is presented. The proposed involves five steps: (1) life cycle assessment, (2) non-dimensional normalization, (3) performance evaluation, (4) centroid-based analysis, (5) impact modeling. findings show that supply chains production sectors accounted for major environmental with higher than 80% portions total carbon footprints. Animal slaughtering, rendering, processing found most dominant in categories. logistic model results revealed overall accuracy equal to 91.67%. Furthermore, among all indicators, it has CO SO2 significant contributors. also 13.7% beverage clustered high, which bread bakery product manufacturing central sector. large value variance (5.24) attributed weighted animal (except poultry) cluster.