Fibonacci Series-Based Pairwise Comparison Scale for Analytic Hierarchy Process

Can Ylldlrlm B., KARAKAYA G., Gönül M. S.

International Journal of Information Technology and Decision Making, cilt.20, sa.3, ss.959-986, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 20 Sayı: 3
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1142/s0219622021500243
  • Dergi Adı: International Journal of Information Technology and Decision Making
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.959-986
  • Anahtar Kelimeler: Numerical comparison, AHP, comparison scale, Fibonacci, exponential, consistency, NUMERICAL SCALES, JUDGMENT SCALES, CONSISTENCY
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

© 2021 World Scientific Publishing Company.The Analytic Hierarchy Process (AHP) is one of the most widely used quantitative tools in multi-criteria decision-making problems. Despite its popularity and use due to its simple but systematic procedure, AHP has limitations especially in terms of the numerical comparison scale used in one of its core steps: pairwise comparisons. AHP is based on verbal comparisons of alternatives/criteria, which are, then, converted into quantitative scores with a one-to-one mapping between the verbal comparisons and a predetermined numerical scale. The choice of the numerical scale affects an essential characteristic of pairwise comparisons: consistency. In order to understand the intrinsic consistency propinquities, this study evaluates the most widely used numerical pairwise comparison scale (Fundamental Scale) and other numerical scales that have been proposed since the initial formulation of AHP. After identifying the limitations of known scales, a new scale based on Fibonacci series is developed considering these limitations, and further analysis is conducted through extensive simulations. The results show that the proposed scale performs well when compared to the other scales.