In contemporary data-intensive environments, organizations increasingly depend on real-time analytics and adaptive visualization frameworks to support time-sensitive decision-making processes. The emergence of digital insight systems—integrated platforms combining data ingestion, processing, and interpretability mechanisms—has significantly transformed how decision-makers interact with complex datasets. This study investigates the integration of configurable visual panels with digital insight systems to enhance responsiveness, interpretability, and operational efficiency in dynamic decision contexts.

The research builds upon theoretical foundations from grey system theory, interpretable machine learning, and explainable artificial intelligence, synthesizing them into a unified framework for decision intelligence. Grey system models, particularly those introduced by Deng Julong, provide a robust basis for handling incomplete and uncertain data environments (Deng, 1985; Deng, 1986; Deng, 1988). Simultaneously, modern interpretability frameworks such as SHAP and LIME offer transparency in predictive analytics, enabling decision-makers to understand model outputs (Lundberg and Lee, 2017; Ribeiro et al., 2016). These paradigms are further enhanced through real-time dashboarding technologies, as demonstrated in enterprise systems utilizing platforms such as PeopleSoft Kibana dashboards (Gondi et al., 2026).

This paper proposes a structured framework that integrates digital insight systems with configurable visual panels to facilitate rapid, accurate, and explainable decision-making. The framework incorporates multi-layer data processing, adaptive visualization components, and interpretability modules. Through analytical modeling and conceptual validation, the study demonstrates how such systems reduce decision latency, improve situational awareness, and support strategic responsiveness.

Key findings highlight that configurable dashboards significantly enhance cognitive processing efficiency by aligning data presentation with user-specific requirements. Additionally, the integration of explainable AI techniques ensures transparency, thereby increasing trust in automated decision-support systems. However, limitations related to scalability, data quality, and interpretability complexity remain critical considerations.

The study contributes to the evolving discourse on decision intelligence by bridging classical uncertainty modeling with modern visualization and interpretability technologies. It provides both theoretical insights and practical implications for deploying real-time decision-support infrastructures in enterprise environments.

Digital Insight Systems, Real-Time Decision Making, Configurable Dashboards, Explainable AI

Deng Julong, "The grey situation decision-making", The fuzzy mathematics. vol. 5 pp. 33-42, 1985.

Deng Julong, "Grey forecasting and decision making", Huazhong University of science and technology press, Wuhan,. 1986.

Deng Julong., "Grey system", China ocean press, Beijing, 1988.

Evans R. and Grefenstette E., “Learning Explanatory Rules from Noisy Data,” Journal of Artificial Intelligence Research (JAIR), 2018.

Doshi-Velez F. and Kim B., “Towards a Rigorous Science of Interpretable Machine Learning,” arXiv preprint, 2017.

Gondi, Sravanthi, Pankaj Arora and Pavan Kumar Rajagopal PrakashKumar. "Utilizing Peoplesoft Kibana and Fluid Dashboards for Real-Time Decision Making." Advances in Consumer Research 3, no. 3 (2026): 657-671.

Liu Sifeng, Dang Yaoguo, Fang Zhigeng, etc. "The theory and application of grey system". The science press, Beijing, 2004.

Liu Zhibin, Zhong Shuang, "Grey situation decision analysis of environmental quality of underground water contaminated by leachate of the dumping area. Journal of liaoning technical university, vol. 24 pp. 129-131, 2005.

Lundberg S. and Lee S.-I., “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems (NeurIPS), 2017.

Ribeiro M., Singh S., and Guestrin C., “Why Should I Trust You? Explaining the Predictions of Any Classifier,” ACM SIGKDD, 2016.