Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Determination of Criteria Priorities and Interactions in ChatGPT by a Fuzzy Model

Çakır Fatma Sönmez, Keleş Nuh

Foundations of Computing and Decision Sciences

2025

Vol. 50, No. 2

207--228

Today, technology is advancing much more and faster than in the past. The technological revolution is progressing so fast that people can now communicate with preprogrammed computers through Artificial Intelligence (AI). This study aims to evaluate the priorities and interactions of the criteria that stand out in the use of ChatGPT-4, using Fuzzy-Analytical Hierarchy Process (F-AHP) and Fuzzy-DEMATEL (F-DEMATEL) methods. Eight critical criteria in the use of ChatGPT are determined by the expert opinions obtained from the focus group. Among the criteria, this study found that reliability 23.1% and security 21.2% were the most important criteria by F-AHP calculations. This study also found that the criteria of appearance and functionality were generally influencing criteria, and the criteria of speed was generally influenced by other criteria.

Comparison of multi-criteria decision-making methods with the same normalization procedure based on real-life applications

Ersoy Nazlı, Keleş Nuh

Operations Research and Decisions

2024

Vol. 34, No. 3

87--100

The ranking of a set of objects defined by a single data set may vary due to differences in multi-criteria decision-making (MCDM) procedures. One of these procedural differences is normalization, which is an important step in data analysis and MCDM methods. In terms of demonstrating the impact of the normalization process on the results, this study aims to compare MCDM methods with a linear normalization process. This study works on eight ranking methods (WASPAS, SECA, SAW, OWA, CODAS, MARCOS, PSI, and WPM), and three weighting methods (Entropy, EW, LOPCOW) based on three reallife applications. The study primarily explains the differences in rankings by the MCDM methods. Additionally, it is also important to demonstrate the impact of different weights on the results. The study found that the MCDM rankings obtained with the same normalization process differed, and it also observed that different criterion weights had an impact on the ranking results. This study contributes to the literature as it is the first to compare MCDM methods using linear normalization processes based on real-life applications.