A methodology for supplier selection under the curse of dimensionality problem based on fuzzy quality function...

Area of Science:

• Operations Research
• Decision Science
• Supply Chain Management

Background:

• Supplier selection is complex, involving vague and imprecise quantitative/qualitative factors.
• Existing methods may struggle with high-dimensional indicator sets and interdependencies.
• Addressing imprecision is crucial for robust supplier evaluation.

Purpose of the Study:

• To propose a novel fuzzy multi-criteria decision-making framework for supplier selection.
• To integrate Quality Function Deployment (QFD) and Interval Data Envelopment Analysis (DEA) for enhanced supplier evaluation.
• To develop a two-stage methodology for indicator screening and supplier selection, mitigating the curse of dimensionality.

Main Methods:

• Constructing a House of Quality (HOQ) to model relationships between product features and supplier evaluation criteria (SEs).
• Employing Interval Data Envelopment Analysis (DEA) to handle imprecise data and evaluate supplier performance.
• Utilizing a forward-stepwise selection approach for screening SE indicators and addressing the curse of dimensionality.

Main Results:

• A novel two-stage supplier selection methodology combining fuzzy QFD and interval DEA was developed.
• The framework effectively screens both indicators and suppliers, even with a high number of indicators.
• Demonstrated applicability through a numerical example and validated stability via sensitivity analysis.

Conclusions:

• The proposed fuzzy QFD and interval DEA integrated framework offers a robust solution for supplier selection under uncertainty.
• The two-phase methodology provides an effective way to screen DEA indicators and select optimal suppliers.
• This research contributes a new approach to multi-criteria decision-making in supplier selection problems.