Methods for Weighting Decisions to Assist Modelers and Decision Analysts: A Review of Ratio Assignment and Approximate Techniques

Barry Ezell,Patrick Hester,Christopher Lynch

doi:10.3390/app112110397

Barry Ezell, Patrick Hester + Show 1 more

Open Access

https://doi.org/10.3390/app112110397

Copy DOI

Abstract

Computational models and simulations often involve representations of decision-making processes. Numerous methods exist for representing decision-making at varied resolution levels based on the objectives of the simulation and the desired level of fidelity for validation. Decision making relies on the type of decision and the criteria that is appropriate for making the decision; therefore, decision makers can reach unique decisions that meet their own needs given the same information. Accounting for personalized weighting scales can help to reflect a more realistic state for a modeled system. To this end, this article reviews and summarizes eight multi-criteria decision analysis (MCDA) techniques that serve as options for reaching unique decisions based on personally and individually ranked criteria. These techniques are organized into a taxonomy of ratio assignment and approximate techniques, and the strengths and limitations of each are explored. We compare these techniques potential uses across the Agent-Based Modeling (ABM), System Dynamics (SD), and Discrete Event Simulation (DES) modeling paradigms to inform current researchers, students, and practitioners on the state-of-the-art and to enable new researchers to utilize methods for modeling multi-criteria decisions.

Highlights

Decision-making processes exist in many forms within computational models and simulations, and varied needs drive the scope of how decision-making is represented across modeling paradigms
Ratio Assignment Techniques ask decision makers questions where answers imply a set of weights corresponding to the user’s subjective preferences. The result of this questioning is a set of scores, or points, assigned to each attribute from which the corresponding weights are calculated after normalizing each attribute score with respect to the total score across all attributes
We provide an overview of the components within Agent-Based Modeling (ABM), System Dynamics (SD), and Discrete Event Simulation (DES) that are relevant to implementing these techniques within a simulation model

Summary

Introduction

Decision-making processes exist in many forms within computational models and simulations, and varied needs drive the scope of how decision-making is represented across modeling paradigms. Many factors can lead to differences in the desired type of decision-making representation utilized within a model, including: differences in the identified relevant model context [5,6,7]; differences in stakeholder perspectives [8,9,10]; differing perspectives on the importance of rare events versus likely outcomes [11]. We may consider cost, size, location, and amenities, whereas a job selection problem may cause us to consider salary, growth potential, location, and benefits. Each of these criteria is important to us and we need to consider them comprehensively to evaluate our problem using multi-criteria decision analysis (MCDA)

Methods

Results

Discussion

Conclusion