Premium
Vendor Selection Using Principal Component Analysis
Author(s) -
Petroni Alberto,
Braglia Marcello
Publication year - 2000
Publication title -
journal of supply chain management
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.75
H-Index - 92
eISSN - 1745-493X
pISSN - 1523-2409
DOI - 10.1111/j.1745-493x.2000.tb00078.x
Subject(s) - principal component analysis , vendor , purchasing , computer science , selection (genetic algorithm) , component (thermodynamics) , process (computing) , bottling line , set (abstract data type) , operations research , business , marketing , machine learning , mathematics , artificial intelligence , engineering , mechanical engineering , physics , bottle , thermodynamics , operating system , programming language
SUMMARY Purchasing managers need to periodically evaluate supplier performance in order to retain those suppliers which meet their requirements in terms of several performance criteria. The evaluation element typically consists of identifying the attributes, criteria, or factors relevant to the decision and then measuring or rating each vendor by considering each of the relevant factors. A critical part of the overall supplier selection process is the determination of the relative importance of each of the factors. This article presents an alternative decision model to evaluate the relative performance of suppliers that have multiple outputs and inputs. This approach is based on a multivariate statistical method, principal component analysis, that uses information obtained from eigenvalues to combine different ratio measures defined by every input and every output. The method has been employed to aggregate multiple performance measures for a real‐world data set of suppliers of a medium‐sized firm operating in the bottling machinery industry.