摘要：This work is devoted to the development of highly efficient tools for making decisions by banking structures to issue and maintain a loan. The developed methodology is intended to support banking services for lending to legal entities. The paper presents the results of a comprehensive analysis of existing methods that can be used to identify scammers, the results of the analysis of data types for solving this problem and ranking them in terms of efficiency. A methodology for building algorithms for searching for scammers is proposed and the application of an algorithm for graph analysis of legal entity relationships for detecting fraud is demonstrated.
