Modeling supplier selection using multi-criterion fuzzy grouping genetic algorithm

Michael Mutingi, Charles Mbohwa

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

2 Citations (Scopus)


Supplier evaluation and selection are a complex problem characterized by fuzzy conflicting decision criteria, and imprecise management goals and aspirations. It was realized in this chapter that a number of conflicting criteria may have to be optimized simultaneously if the solution is to be satisfactory. Some of the criteria that were noted are price, lead time, quality, and number of suppliers or vendors selected. Based on an example of subcontractor selection, this chapter presented the supplier selection problem as a grouping problem where groups of tasks (items) can be assigned to each subcontractor, but at a specific cost. It was noted that in the subcontractor selection problem, the tasks may have due dates and precedence constraints, which make the problem even more complicated. This calls for advanced efficient, flexible, and interactive decision support systems that can handle fuzzy variables. To effectively address the fuzzy properties of the problem, a fuzzy multi-criterion grouping genetic algorithm was proposed to model the subcontractor selection. The algorithm uses a fuzzy evaluation approach to convert management goals and aspirations into normalized fuzzy membership functions. Further applications of this model can be applied to similar supplier evaluation and selection problems characterized with (i) multiple suppliers and multiple commodities, (ii) multiple and often conflicting imprecise decision criteria, and (iii) due date restrictions, and/or precedence constraints.

Original languageEnglish
Title of host publicationStudies in Computational Intelligence
PublisherSpringer Verlag
Number of pages16
Publication statusPublished - 2017

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Modeling supplier selection using multi-criterion fuzzy grouping genetic algorithm'. Together they form a unique fingerprint.

Cite this