Manuscript received July 4, 2026; accepted August 1, 2026; published September 23, 2026
Abstract—Selecting environmentally sustainable host cities for mega-events requires comparing multiple conflicting indicators without a ground-truth ranking. We propose a fully data-driven framework combining entropy-based feature weighting, an ensemble of TOPSIS and PROMETHEE II, multi-scale Monte Carlo and Bayesian-bootstrap uncertainty quantification, and clustering-based tier discovery. Applied to seven environmental indicators for 30 NFL metropolitan areas, the framework ranks New York City first (TOPSIS C = 0.817) with a 100% top-three probability across all perturbation scales. TOPSIS and PROMETHEE II show near-perfect agreement (Kendall's τ = 0.954), while entropy weights align moderately with LASSO (τ = 0.619). Clustering identifies two natural sustainability tiers, and a three-tier partition aligns well with the ranking (ARI = 0.78). A GHG-only ranking is largely unrelated to the multidimensional assessment (τ = 0.085). Using only public data and no expert elicitation, the approach provides a transparent, reproducible framework for sustainable host-city selection that generalizes to other events and city sets.
Keywords—unsupervised feature importance, ensemble decision making, uncertainty quantification, TOPSIS, PROMETHEE, entropy weighting, clustering, environmental sustainability, Super Bowl
Cite: Jin Peiyuan, "Data-Driven Environmental Ranking of Mega-Event Host Cities: Unsupervised Feature Weighting, Multi-Algorithm Ensemble, and Uncertainty Quantification," International Journal of Engineering and Technology, vol. 18, no. 3, pp. 165-169, 2026.
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (
CC BY 4.0).
