• S. Maksymchuk Master student University of Customs and Finance
  • L. Кабак Associate Professor of Department of Software Engineering NTU Dnipro Polytechnic
  • B. Moroz Professor of Department of Software Engineering NTU Dnipro Polytechnic
Keywords: Oracle database, data mining, anomaly detection, customs, risk management system


Nowadays using of data mining analytics is actual question. Data mining techniques and their algorithms are becoming more common and necessary. Data warehouses stores very big amount of data at the moment and their volume increases every day. Performing analysis of data with data mining techniques and algorithms allows to detect new potentially helpful and beneficial patterns in data that can be used to make prediction. So getting results of predictive analytics helps to make right business decisions for entrepreneur and solve many issues for government institution.
Customs of developed countries started using data mining through integration of data mining tools in the risk management systems to detect fraud behavior and get other useful information from data as well. It is possible to find some study related to this issue.
Risk management systems which are used by Ukrainian customs does not support data mining tools. Simultaneously, Ukrainian customs uses Oracle Database as well. So using data mining techniques and algorithms build-in Oracle Database is obvious step to extend the available risk management system and keep up to date. So this work reveals modern tendencies and importance of integration data mining technology in business and public administration.
In this article have been considered data mining techniques, modern tendencies of the usage data mining technology by customs, integration of such a technology in the risk management systems so as to detect fraud behavior and get other potentially useful predictions based on data has been collected before. You can find brief descriptions of data mining techniques such as anomaly detection, сlassification, clustering, regression, anomaly detection in this article as well as real-world examples how each of this techniques can be applied for customs need. Also here have been technic for analysis tables which store data of export and import operations in order to detect fraud behavior. The results
have been described in this work and it have been represented graphically. proposed, designed, implemented and described real scenario of usage Oracle Data Mining in customs, in particular usage of anomaly detection


Top 33 Data Mining software [Electronic resource] – Access mode:

50 top free data mining software [Electronic resource] - Access mode:

Brendan Tierney Predictive Analytics Using Oracle Data Miner: Develop & Use Data Mining Models in Oracle Data Miner, SQL & PL/SQL: - Oracle Press, 2014. – 429 - ISBN: 978-0-07-182175-9

Oracle Advanced Analytics Customer Success Stories [Electronic resource] – Access mode:

Geourjon A.M. , B. Laporte, Coundoul, O., et M. Gadiaga. 2012. "Inspecting Less to Inspect Better : The Use of Data Mining for Risk Management by Customs Administrations", in Reform by numbers : Measurement Applied to Customs and Tax Administrations in Developing Countries, ed. T. Cantens, R. Ireland and G. Raballand. Washington, DC : World Bank, November.

Habibollah Arasteh Rad *, Saeed Arash , Farhad Rahbar , Ruhollah Rahmani , Zainabolhoda Heshmati , Maysam Mirzaee Fard (2015). A Novel Unsupervised Classification Method for Customs Fraud Detection. Indian Journal of science and technology, 8(35), DOI: 10.17485/ijst/2015/v8i35/87306

V DFS funktsIonuE suchasna avtomatizovana sistema mitnogo kontrolyu ta oformlennya [Elektronniy resurs] – Rezhim dostupu:

Elektronna mitnitsya [Elektronniy resurs] – Rezhim dostupu:

Marchenko O.O., Rossada T.V. AktualnI problemi Data Mining: Navchalniy posIbnik dlya studentIv fakultetu komp’yuternih nauk ta kIbernetiki. — Kiyiv. — 2017. — 150 s.

How to Cite
Maksymchuk, S., КабакL., & Moroz, B. (2019). USING OF THE MODERN DATA MINING TECHNICS IN CUSTOMS OF UKRAINE. Systems and Technologies, 2(58), 33-49.