OSWMI: An objective-subjective weighted method for minimizing inconsistency in multi-criteria decision making

In Multi-Criteria Decision Making (MCDM), alternatives are evaluated by considering different criteria. In MCDM, there is a requirement to integrate the objective and subjective weights, since the objective weighting methods ignore the decision-maker's (DM's) experiences and the subjective weighting methods ignore the performance ratings of the alternatives with respect to different criteria. To integrate the two types of weights and evaluate the best alternative, three well-established methods, namely CRiteria Importance Through Intercriteria Correlation (CRITIC), Best Worst Method (BWM), and LINear programming techniques for Multidimensional Analysis of Preferences (LINMAP) are considered in our study. Based on these methods, we have proposed a new method, namely Objective-Subjective Weighted method for Minimizing Inconsistency (OSWMI) which considers both pairwise comparisons of the criteria and alternatives along with their corresponding performance ratings. We have first improved both the methods, CRITIC (named as improved CRITIC) and LINMAP (named as LINMAP II). Finally, the proposed OSWMI method is developed by integrating the improved CRITIC method, BWM, and LINMAP II using a multi-objective non-linear programming (MONLP) model. The OSWMI method may reduce the problem of strategic weight manipulation, since the integrated weights and the two ideal solutions are priori unknown and obtained simultaneously for selecting the best alternative. A case study of the web service selection is used to demonstrate the implementation of the OSWMI method. From the analysis, the proposed OSWMI method reveals a promising result. Further, sensitivity of the OSWMI method is checked by using the standard regression coefficients obtained by multiple linear regression.

Automated summary

In Multi-Criteria Decision Making (MCDM), it is necessary to integrate objective and subjective weights to evaluate alternatives. This study proposes a new method called OSWMI, which combines the CRITIC, BWM, and LINMAP methods and considers pairwise comparisons and performance ratings. The OSWMI method can reduce weight manipulation and has promising results.