Towards Enhancing Computational Complexity in Explainable Decision Support System: Exploring Bio-Inspired Approaches

Decision support systems play an important role in aiding decision-making processes by providing valuable insights and recommendations driven by data analysis. However, as decision support systems increasingly employ complex Artificial Intelligence (AI) techniques, the need for explainability becomes essential to build trust and transparency with users. As a result, explainable AI (XAI) has emerged as a paradigm that seeks to make AI decision-making processes transparent and understandable to humans. While explainability enhances user comprehension, it introduces computational complexity challenges. In the evolving landscape of Explainable Decision Support Systems (XDSS), the quest for optimizing computational complexity without sacrificing explainability presents a challenge. This paper delves into the potential of bio-inspired algorithms as a novel approach to addressing this challenge. Through a comprehensive theoretical analysis, this paper explores various bio-inspired algorithms, such as Genetic Algorithms, Particle Swarm Optimization, and Ant Colony Optimization, to assess their applicability and effectiveness in enhancing the computational efficiency of XDSS. By establishing a set of selection criteria to identify the most promising bio-inspired algorithm for optimizing computational complexity in XDSS. The paper sets the groundwork for future research by highlighting theoretical foundations, potential applications, and a clear direction for empirical validation. This exploration not only contributes to the theoretical advancement in the field of XDSS but also opens new avenues for practical implementations that can significantly improve explainable decision support systems’ performance and usability.