This study presents a framework for evaluating and monitoring the performance of Original Equipment Manufacturers (OEMs) supplying an automobile manufacturer. It combines fuzzy VIKOR with cluster analysis to rank suppliers and group them by performance.
Article Info
- Author: Saad Parvez
- Journal: Materials Today: Proceedings
- Year: 2020
- Volume and issue: Volume 27, Part 2
- Pages: 1411–1416
- Author affiliation: Mechanical Engineering Department, NIT Srinagar, Hazratbal, J&K 190006, India
- Received: 23 December 2019
- Revised: 20 February 2020
- Accepted: 23 February 2020
- Available online: 22 April 2020
- Version of Record: 23 June 2020
- DOI: 10.1016/j.matpr.2020.02.785
Study purpose
The article addresses the need to monitor current OEMs as well as select suppliers. It proposes a framework to measure and quantify supplier performance, rank the alternatives, and classify them into groups that can inform strategic partnerships.
Methodology
The study applies its framework to twenty OEMs supplying different components to a major automobile manufacturer in India. The suppliers were selected using Pareto-based ABC analysis. Twelve standard attributes were identified as evaluation criteria.
Decision-makers’ survey judgments can be uncertain or imprecise. Fuzzy VIKOR translates linguistic assessments into fuzzy values and then defuzzifies them to obtain crisp priority scores on a common scale. The researchers then apply cluster analysis to those scores to identify suppliers with similar performance. The source describes distance-based dynamic clustering and K-means, and reports using IBM SPSS 23 and MATLAB for the clustering work.
Findings and implications
The framework produces three supplier clusters, named PROMINANTS, INTERMEDIATORS, and MARGINALS. The reported optimum fuzzy VIKOR clustering contains five, five, and ten data points in the respective groups, with a cluster ratio of 1.2072 at the 75th iteration.
The proposed approach provides managers with a way to translate expert judgments into comparable supplier performance priorities, then view those results as groups for performance monitoring. The article notes that the framework was developed for an automobile sector application and could also be adopted by other sectors.
Cite this paper
APA: Parvez, S. (2020). Application of fuzzy VIKOR and cluster analysis for performance evaluation of Original Equipment Manufacturers. Materials Today: Proceedings, 27(Part 2), 1411–1416. https://doi.org/10.1016/j.matpr.2020.02.785
MLA: Parvez, Saad. “Application of Fuzzy VIKOR and Cluster Analysis for Performance Evaluation of Original Equipment Manufacturers.” Materials Today: Proceedings, vol. 27, part 2, 2020, pp. 1411–1416. https://doi.org/10.1016/j.matpr.2020.02.785.
IEEE: S. Parvez, “Application of fuzzy VIKOR and cluster analysis for performance evaluation of Original Equipment Manufacturers,” Materials Today: Proceedings, vol. 27, pt. 2, pp. 1411–1416, 2020, doi: 10.1016/j.matpr.2020.02.785.
Source
Consult the publisher’s original page for this article’s complete record. View the article on ScienceDirect.
Use Fuzzy VIKOR to rank suppliers under uncertain, linguistic performance judgments.