A Hybrid GA-MOORA Approach for Objective Criteria Weighting in Multi-Criteria Decision Making

Abstract

Multi-Criteria Decision-Making (MCDM) plays a critical role in identifying optimal solutions in complex environments where multiple, often conflicting, criteria must be considered. This paper presents a hybrid Artificial Intelligence (AI) framework that integrates a Genetic Algorithm (GA) with the Multi-Objective Optimization by Ratio Analysis (MOORA) method. The GA provides global search and optimization capabilities for determining criterion weights, while MOORA offers a computationally simple, robust, and rank-stable approach for evaluating alternatives. The proposed methodology consists of three stages: 1) identifying the decision alternatives and relevant evaluation criteria, 2) determining the criteria weights using a GA, and 3) ranking the alternatives using the MOORA method. The effectiveness of the hybrid GA–MOORA approach is validated through a comparative case study based on the dataset from [11] to determine the optimal weighting factors. Results demonstrate a strong agreement between MOORA and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). Both methods identify Alternative 1 (q = 0.9) as the least favorable option (ranked 5th), while the mid-range alternatives (Alternatives 4 and 5) exhibit similar rankings. The proposed GA-MOORA model identifies Alternative 3 (q = 0.5) as having the highest net utility, with Alternative 2 (q = 0.3) performing comparably. This close performance provides decision-makers with flexible, reliable options for final selection.