KnE Social Sciences

Published date: Feb 15 2018

Journal Title: KnE Social Sciences

Issue title: III Network AML/CFT Institute International Scientific and Research Conference "FinTech and RegTech"

Pages: 444-449

DOI: 10.18502/kss.v3i2.1575

Prikazchikova A.S.aska4.92@mail.ruNRNU "MEPhI" post-graduate student, leading expert of the Rosfinmonitoring Information Systems Development Department, Moscow

Prikazchikova G.S.Associate Professor of the Russian Customs Academy, Moscow

The article considers the binary classification problem of economic security objects on the credit institutions example, for which it is proposed to use machine learning methods. In the study process the expediency of one of the methods of machine learning — the method of k-nearest neighbors — was proved to solve this problem, its efficiency amounted 

to 84 %.

Key words: machine learning methods, financial statements, performance indicators, credit institutions, binary classification, k-nearest neighbors method.

[1] Denisenko, A.S. Information system for processing financial monitoring data in the field of bioresources [Text]: author’s abstract. dis. on comp. of the Cand.Tech.Sci scientific degree. (05.13.01) / Denisenko Andrey Sergeevich; NRNU ”MEPI”. – Moscow, 2017. – 29 p.


[2] Abidin, T. and Perrizo, W. SMART-TV: A Fast and Scalable Nearest Neighbor Based Classifier for Data Mining. Proceedings of ACM SAC-06, Dijon, France, April 23-27, 2006. ACM Press, New York, NY, pp.536-540.


[3] Apostolos Papadopoulos, Yannis Manolopoulos. Performance of Nearest Neighbor Queries in R-Trees Source // Proceedings of the 6th International Conference on Database Theory. 1997. P. 394 – 408.