Рақамли технологияларнинг назарий ва амалий масалалари Volume 8 Issue 1 (2025) · pp. 114-121
Self-adaptive agent model for Pareto-optimal decision-making in business intelligence systems
Eshankulov, H.I., Murodova, R.B.
Abstract
This article proposes a conceptual approach to optimizing decision-making processes in Business Intelligence systems based on the Pareto-optimal approach and the concept of self-adaptive agents. Business Intelligence systems enable modern organizations to process and analyze large volumes of data and automate strategic decision-making processes. However, traditional approaches often have limitations in enhancing decision-making efficiency.To address this issue, the article presents a new model developed based on multi-agent systems. In the proposed model, self-adaptive agents formulate Pareto-optimal decisions by collecting, processing, and analyzing data in real-time. This approach increases the adaptability of Business Intelligence systems and allows for the selection of the most optimal decisions considering various factors.The article provides a detailed analysis of the role of self-adaptive agents, their functional capabilities, and the advantages of the Pareto-optimal approach. Based on experimental results, the effectiveness of the proposed model is evaluated, highlighting its advantages over traditional Business Intelligence systems.The research results indicate that the Pareto-optimal approach based on self-adaptive agents plays a crucial role in improving the speed, accuracy, and adaptability of decision-making in Business Intelligence systems. Therefore, this model can be considered a promising solution for more efficient and intelligent management of Business Intelligence systems.
BI tizimlariko‘p agentli tizimlarmoslashtiruvchi agentlarPareto-optimal qarorlarko‘p mezonli qarorlarma’lumot tahliliBusiness Intelligence systemsmulti-agent systemsself-adaptive agentsPareto-optimal decisions
Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.