Zhixian Zhang
School of Professional Studies, New York University, New York, NY 10003, USA.
*Corresponding author: Zhixian Zhang
Abstract
For intelligent decision-making tasks in complex scenarios, the stability and response efficiency of AI system performance have gradually become the key metrics for evaluating the quality of system deployment. In the context of the dynamic evolution of task requirements and increasing heterogeneity of input data, static assessment methods are unable to accurately reflect the system’s operational performance or issue effective warnings for potential performance degradation. Based on the “monitoring - feedback - optimization” operational closed-loop logic, this paper proposes a system mechanism framework that integrates real-time monitoring and data-driven optimization. This framework constructs a performance monitoring matrix covering multiple dimensions such as response speed, accuracy, and resource utilization, and is supported by a high-frequency data feedback path and a lightweight modeling platform, enabling online analysis and dynamic correction of model behavior. Additionally, a plug-in optimization module is introduced, leveraging reinforcement learning strategies to drive adaptive adjustment of system parameters. In complex tasks, this approach demonstrates stronger stability and task-matching capabilities, providing theoretical support and engineering direction for building decision-oriented AI systems with long-term adaptability.
References
[1] Nozari H, Jarosz SA. Quantitative decision making in reverse logistics with a hybrid decision support system integrating agentic AI and evolutionary optimization. Euro-Mediterr J Environ Integr. 2025;11(1):30.
[2] Salimparsa M, Sedig K, Lizotte JD, et al. Explainable AI for Clinical Decision Support Systems: Literature Review, Key Gaps, and Research Synthesis. Informatics. 2025;12(4):119.
[3] Domingues SN. A hybrid decision support system using rule-based and AI methods: the OnCATs knowledge-based framework. Int J Med Inform. 2025;206:106144.
[4] Vishwakarma KA, Patro KP, Acquaye A. Applications of AI to low carbon decision support system for global supply chains. Clean Logist Supply Chain. 2025;17:100261.
[5] Shan S, Li Y. Research on the Application Framework of Generative AI in Emergency Response Decision Support Systems for Emergencies. Int J Hum-Comput Interact. 2025;41(15):9191-9208.
[6] Ackerhans S, Wehkamp K, Petzina R, et al. Perceived Trust and Professional Identity Threat in AI-Based Clinical Decision Support Systems: Scenario-Based Experimental Study on AI Process Design Features. JMIR Form Res. 2025;9:e64266.
[7] Arthi R, Krishnaveni S. Optimized Tiny Machine Learning and Explainable AI for Trustable and Energy-Efficient Fog-Enabled Healthcare Decision Support System. Int J Comput Intell Syst. 2024;17(1):229.
[8] Parkavi R, Karthikeyan P, Abdullah SA. Enhancing personalized learning with explainable AI: A chaotic particle swarm optimization based decision support system. Appl Soft Comput. 2024;156:111451.
[9] Wang J, Zhao M, Li Y, et al. Managerial decision support system using an integrated model of AI and big data analytics. Ann Oper Res. 2022;326(Suppl 1):1-18.
Copyright
© 2026 by the author(s).
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives (CC BY-NC-ND) license, which permits non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited and is not modified or adapted.
https://creativecommons.org/licenses/by-nc-nd/4.0/
How to cite this paper
Research on Performance Monitoring and Data-driven Optimization Mechanisms for AI Systems Oriented Toward Decision Support
How to cite this paper: Zhixian Zhang. (2026) Research on Performance Monitoring and Data-driven Optimization Mechanisms for AI Systems Oriented Toward Decision Support. Advances in Computer and Communication, 7(2), 67-71.
DOI: http://dx.doi.org/10.26855/acc.2026.06.001