An improved weighted principal component analysis integrated with TOPSIS approach for global financial development ranking problem of Middle East countries. (12th April 2022)

• Record Type: Journal Article
• Authors: Heydari, Ahmad; Niroomand, Sadegh; Garg, Harish
• Is Part Of: Concurrency and computation. Volume 34:Number 13(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-04-12
• Subjects: feature selection -- financial development -- multi‐criteria decision making -- weighted PCA; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.6923
• Languages: English
• ISSNs: 1532-0626

Abstract

Abstract: Financial development means some improvements on providing the information about investment possibilities in a region or country. In this study, a new perspective of financial development is considered which is called the multi‐criteria global financial development‐ranking problem. In this problem, some countries from the Middle East are considered to be ranked according to the criteria of global financial development from the world bank database. Due to high number of criteria that may affect the quality of the obtained ranking negatively, a solution methodology in three stages is proposed. First, as a novelty, an improved version of the weighted principal component analysis (PCA) approach is proposed to select the most important criteria from the initial set of criteria and also determine their importance weights. This approach considers both linear and nonlinear relationships of the data instead of considering just linear relationships. Then using the reduced decision matrix and the obtained importance weight values, the technique for order of preference by similarity to ideal solution multi‐criteria decision approach is used to rank the countries of case study. The computational study is done based on the proposed improved weighted PCA approach and the obtained results are analyzed and compared by those of the classical approaches, for example, some versions of the classical weighted PCA approach.