EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ES‐SORM: A Ranking Operator With Anchored Normalization and Structured Output

Ömer Faruk Rençber

International Journal of Intelligent Systems · 2026-01 · 2026 (1)

DOI: 10.1155/int/3335365 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Intelligent Systems, online erschienen am 15.07.2026. Verfasst von Ömer Faruk Rençber. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study addresses two persistent structural problems in multicriteria decision analysis that directly affect the reliability and interpretability of ranking results: ranking instability when the alternative set changes and the reduction of decision output to a single score or rank. In classical methods, normalization is typically built from within‐sample references, while robustness information is reported separately from the ranking operator. Together, these practices weaken transparency and reproducibility. In response, we propose Enhanced Structured Object Ranking Method (ES‐SORM), a ranking operator based on anchored normalization and structured output. The method integrates fixed reference anchors, pooled reference weights, profile‐based normative assessment, and a structured output object within a unified framework. The empirical evaluation compares ES‐SORM with TOPSIS and PROMETHEE II across three synthetic stress regimes: alternative removal, clone addition, and data‐noise perturbation. Under the composition‐change protocol used in this study, ES‐SORM achieves Max Shift = 0. Under data noise, it remains in the same performance band as the benchmark methods. A real‐data application on the 2023 environmental, social, and governance blocks of OECD countries provides secondary evidence that this pattern also appears in an external context. The primary contribution of this study is not a new scoring function but a fixed‐reference protocol that combines pool‐anchored normalization, pooled CRITIC weights, and a structured output object: under this protocol, composition invariance follows by construction (Proposition 1), and the hybrid fusion term contributes to discrimination rather than to the invariance result. ES‐SORM addresses one specific source of order reversal—volatility introduced by alternative‐set‐derived normalization—and is not proposed as a general elimination of all forms of rank reversal; the structured output object is a transparency layer that exposes residual order stability rather than a mechanism that prevents reversal from other sources.

Zitieren

APA

Rençber, Ö. F. (2026). ES‐SORM: A Ranking Operator With Anchored Normalization and Structured Output. International Journal of Intelligent Systems, 2026(1). https://doi.org/10.1155/int/3335365

Vancouver

Rençber ÖF. ES‐SORM: A Ranking Operator With Anchored Normalization and Structured Output. International Journal of Intelligent Systems. 2026;2026(1). doi:10.1155/int/3335365

BibTeX
@article{Renber2026,
  author = {Rençber, Ömer Faruk},
  title = {ES‐SORM: A Ranking Operator With Anchored Normalization and Structured Output},
  journal = {International Journal of Intelligent Systems},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/int/3335365}
}
Kostenlos starten →