Generalised framework for multi-criteria method selection (1810.11078v1)

Abstract: Multi-Criteria Decision Analysis (MCDA) methods are widely used in various fields and disciplines. While most of the research has been focused on the development and improvement of new MCDA methods, relatively limited attention has been paid to their appropriate selection for the given decision problem. Their improper application decreases the quality of recommendations, as different MCDA methods deliver inconsistent results. The current paper presents a methodological and practical framework for selecting suitable MCDA methods for a particular decision situation. A set of 56 available MCDA methods was analyzed and, based on that, a hierarchical set of methods characteristics and the rule base were obtained. This analysis, rules and modelling of the uncertainty in the decision problem description allowed to build a framework supporting the selection of a MCDA method for a given decision-making situation. The practical studies indicate consistency between the methods recommended with the proposed approach and those used by the experts in reference cases. The results of the research also showed that the proposed approach can be used as a general framework for selecting an appropriate MCDA method for a given area of decision support, even in cases of data gaps in the decision-making problem description. The proposed framework was implemented within a web platform available for public use at www.mcda.it.

• The paper introduces a rule-based decision tree that systematically narrows down 56 MCDA methods to improve decision-making accuracy.
• It classifies methods by various descriptors—such as weighting, performance scale, and uncertainty handling—to guide precise method selection.
• The proposed online platform, mcda.it, demonstrates practical application by ensuring consistent and robust selection in real-world decision scenarios.

Overview of a Generalised Framework for Multi-Criteria Method Selection

The paper presents a comprehensive framework for the systematic selection of Multi-Criteria Decision Analysis (MCDA) methods, addressing a critical gap in decision-making processes across various domains. MCDA techniques are integral to handling multifaceted decision problems that involve multiple, often conflicting, criteria. Despite the development of diverse MCDA methods, a key challenge has been the selection of the most suitable method for specific decision problems. This selection is imperative as incorrect choices can jeopardize the quality of decision-making outcomes.

The authors analyze a vast array of 56 MCDA methods, developing a hierarchical framework that classifies these methods by characteristics integral to the decision-making process. This classification comprises multiple descriptors including the type of weighting used, scale of criteria performance, handling of uncertainty, and the decision problem's nature. Notably, the paper proposes a decision support system that navigates the uncertainty in decision-making scenario descriptions, ensuring practitioners can pinpoint appropriate MCDA methods even when full problem clarity is lacking.

Methodological Contributions

The methodological innovation lies in the creation of a rule-based guidance system tailored to diverse MCDA method characteristics. By coupling this with a hierarchical decision tree, it becomes feasible to sequentially eliminate unsuitable methods, thereby optimizing the method selection process. This formal structure enables precision even amidst partial data gaps—a prevalent reality in decision scenarios.

One of the pivotal contributions is the framework’s allowance for uncertainty, a frequently encountered challenge in real-world decision-making. The approach not only accounts for incomplete problem descriptions but also evaluates the implications of such uncertainty on method selection. Thereby, it broadens the efficacy of MCDA by enhancing the robustness of method selection processes in varied contexts.

Practical and Theoretical Implications

The practical implications are substantial; the introduction of an online platform for public use (mcda.it) demonstrates the usability and accessibility of the proposed framework. This platform could serve as a valuable tool for decision-makers, enhancing the rigour and consistency of method selection in strategic and operational decisions.

From a theoretical standpoint, this paper contributes significantly to the literature on decision support systems. By structuring a decision-tree framework that systematically accounts for method characteristics and decision problem descriptors, it extends existing knowledge on decision aid systems. The inclusion of fuzzy set theory for handling uncertainty reflects an understanding of contemporary methodological enhancements in decision science.

Speculations on Future Research Directions

The presented framework lays the groundwork for intriguing future research opportunities. Extending the database to include group decision-making scenarios could be one such avenue, given the prevalence of collaborative decision contexts across industries. Furthermore, enhancing the rule set to incorporate emerging MCDA methods, and refining it to cater to modern computational approaches, could bolster the adaptability and contemporary relevance of this framework.

Lastly, developing a nuanced ontology of decision problems and MCDA methods could elevate the decision-making field, facilitating semantic searches and classifications that enhance the precision and user-friendliness of decision support systems. This endeavor could significantly benefit interdisciplinary applications where decision-making precision is paramount.

In summary, this paper delineates a structured, methodical approach to MCDA method selection that reconciles the challenges of uncertainty and variability in decision problems with a robust, hierarchical framework. The integration of this approach within a publicly accessible digital tool signifies a forward-thinking initiative, significantly advancing the domain of decision support systems.