Formation of an Analytical Body for Monitoring the Key Results of a Fintech Organization

Yu. A. Rakovskaya (), A. V. Saharov (), A. D. Sakhno () and M. B. Laskin ()

Administrative Consulting, 2026, issue 5

Abstract: The management of large organizations, including fintech organizations, often needs feedback from consumers of goods and services in order to assess how well the strategic goals of the organization and the tasks resulting from them are being fulfilled. The external information field can be considered as a source of data that allows you to get feedback from users and assess whether the goals and objectives set by management are being achieved. The large size of the resulting text data corpuses suggests the construction of a technique for automatically collecting text information for subsequent processing and analysis, also in automatic mode. The article presents a comprehensive methodology for the formation of an analytical corpus of publications from open sources for subsequent monitoring of the external information environment. Eight types of information sources are considered (mass media, blogs, social networks, reviews, forums, video hosting, microblogs, messengers). Selecting the types of sources and assessing their importance for a specific key result is the main stage of the methodology: the language model translates the business formulation of the goal into thematic features and priorities of sources, which affects the completeness and relevance of the generated corpus. Therefore, the choice of the LLM model is considered in the work as an essential part of the methodology, requiring justification and verification. The paper compares nine different LLM models for ranking types of sources, and evaluates the quality of ranking for five selected key results. The nDCG@8 metric was used for the assessment. The best metric value was obtained for the Claude Sonnet 4 model.6. The paper proposes a technique for solving the problem of message duplication, which made it possible to reduce the volume of records in the database by 15% on the generated data bodies. An intelligent agent has been developed to collect information from external sources.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.acjournal.ru/jour/article/viewFile/3069/2179 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:acf:journl:y:2026:id:3069

Access Statistics for this article

More articles in Administrative Consulting from Russian Presidential Academy of National Economy and Public Administration. North-West Institute of Management.
Bibliographic data for series maintained by ().