Prisma Guided Systematic Review of Large Language Model (LLM) Applications in Business Intelligence
Makaleler > Derleme · 2025
Yazarlar: İbrahim YÜLÜCE, Fatih Dagdeviren, Murat Orun, Ismail Duran, Orhan DAĞDEVİREN
2025 9th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Uluslararası, 2025, ss 1-6
DOI: 10.1109/ismsit67332.2025.11267912
Özet
Business Intelligence (BI) refers to a set of architectures, tools, and methods designed to transform raw corporate data into meaningful insights, enabling data-driven decision-making at all levels of an organization. In this paper, we provide a PRISMA 2020–guided systematic review that examines the integration of large language models (LLMs) into BI work-flows. The most prominent themes emerging from the literature were natural language querying and text-to-SQL translation. To facilitate comparative analysis and provide a consolidated overview of the BI–LLM landscape, this review offers a shareable, coded dataset. The findings suggest that LLMs currently enhance the user-interaction layer of BI. Although applications remain limited, research activity in this area has grown significantly, highlighting both the opportunities and the lack of systematic integration of LLMs into BI workflows. Existing studies are largely exploratory and methodologically fragmented, emphasizing the need for integrated conceptual frameworks and robust empirical evidence. By tracing this trajectory, the review establishes a structured foundation for more rigorous and cumulative research on the BI–LLM interface.