Enterprise Explainable Decision Intelligence Framework (EEDIF): A Service-Oriented Architecture for Trustworthy AI Decision Support

This paper presented the Enterprise Explainable Decision Intelligence Framework (EEDIF), a service-oriented architecture that introduces explainability as a reusable enterprise capability for trustworthy AI decision support. The proposed architecture separates explainability from AI prediction models through the Enterprise Explainability Service (EES), enabling standardized explanation generation, feature attribution, confidence assessment, policy validation, and audit logging across enterprise applications. A loan approval decision support case study demonstrated how the proposed architecture can be integrated into enterprise workflows without modifying underlying AI models. The qualitative evaluation further showed that EEDIF supports transparency, governance, auditability, scalability, and reusability, providing a practical foundation for enterprise adoption of trustworthy AI. Future work includes implementing the proposed architecture in operational enterprise environments, conducting quantitative evaluations across multiple application domains, and extending the framework to support emerging explainability techniques and evolving AI governance standards.

[1]          A. Adadi and M. Berrada, “Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI),” IEEE Access, vol. 6, pp. 52138–52160, 2018. [2]          S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774. [3]          M. T. Ribeiro, S. Singh, and C. Guestrin, “Why Should I Trust You? Explaining the Predictions of Any Classifier,” in Proc. ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 1135–1144. [4]          R. Guidotti, A. Monreale, F. Turini, D. Pedreschi, and F. Giannotti, “A Survey of Methods for Explaining Black Box Models,” ACM Computing Surveys, vol. 51, no. 5, pp. 1–42, 2018. [5]          N. Barredo Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges Toward Responsible AI,” Information Fusion, vol. 58, pp. 82–115, 2020. [6]          D. Gunning and D. Aha, “DARPA’s Explainable Artificial Intelligence (XAI) Program,” AI Magazine, vol. 40, no. 2, pp. 44–58, 2019. [7]          T. Erl, Service-Oriented Architecture: Concepts, Technology, and Design. Upper Saddle River, NJ, USA: Prentice Hall, 2005. [8]          M. Fowler, Patterns of Enterprise Application Architecture. Boston, MA, USA: Addison-Wesley, 2002. [9]          ISO/IEC 23053:2022, Framework for Artificial Intelligence Systems Using Machine Learning. Geneva, Switzerland: International Organization for Standardization, 2022. [10]          National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0). Gaithersburg, MD, USA: NIST, 2023.