Past efforts in determining suitable normalization methods for multi-criteria decision-making: A short survey

Area of Science:

• Operations Research
• Decision Science
• Data Science

Background:

• Multi-criteria decision-making (MCDM) techniques rely on normalizing incommensurable data.
• Various normalization methods exist, yielding different results with MCDM techniques.
• Selecting appropriate normalization methods is critical, especially with big data.

Purpose of the Study:

• To systematically review and analyze existing literature comparing normalization methods for MCDM.
• To identify gaps and limitations in current research on normalization method suitability.
• To provide insights for future research directions in this domain.

Main Methods:

• Literature search on Google Scholar using keywords 'normalization' and 'MCDM'.
• Analysis of extracted articles based on normalization methods, MCDM methods, and comparison metrics.
• Data analysis facilitated by Tableau software.

Main Results:

• Identified five key limitations in the current body of literature.
• Detailed the normalization methods, MCDM techniques, and comparison metrics employed in previous studies.
• Highlighted the variability in MCDM outcomes based on different normalization approaches.

Conclusions:

• This study is the first to compile and review investigations on ideal normalization methods for MCDM.
• The findings underscore the need for careful selection of normalization techniques.
• Recommendations for future research are provided to address identified limitations.