Comparison of three LDA, PCA and ICA Fast methods using fourteen data analysis algorithms to develop a risk assessment management model for export declarations to deal with illegal trade in Iran customs

Document Type : Research Paper

Authors

1 Department of Public-Financial Management, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

2 Department of Economics, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

3 Faculty of Computer Engineering and Information Technology, Payame Noor University, Tehran, Iran

4 dFaculty of Engineering, Department of Computer, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

Abstract

Risk assessment is the main component of risk management, therefore, developing a suitable data analysis model is particularly important in customs. The purpose of this research is to use data mining techniques to develop an intelligent model for timely prediction of the risk level of export declarations in customs and as a result to prevent irreparable damages. Data mining techniques have been used in this research considering the data-oriented statistical population. The statistical data of the cross-border trade system of the Iranian customs is 698,781 data of the export declaration of the entire customs of the country of Iran for the year 2019-2020. Using Python programming language, feature reduction and effective feature extraction were performed after data preprocessing and preparation, with three methods of principal component analysis, linear differential analysis, and fast independent component analysis. Then for the predictive modelling of fourteen classification algorithms, three methods of principal component analysis (PCA), linear discriminant analysis (LDA) and fast independent component analysis (Fast ICA) were used and eighty percent of the training data were used. After training the models, forty-two different models were extracted. For testing, the obtained models were tested with twenty percent of the data. The test results of the models were compared with standard metrics to evaluate the efficiency of the models and the model obtained from the random forest algorithm with the fast independent component analysis method with three features was selected as the best model for predicting and determining the risk level of export declarations in customs.

Keywords

[1] V. Afanasieva, L. Ivanov, and D. Yanushkevych, Modern approaches to risk management and their use in customs, Traektoriˆa Nauki Path Sci. 3 (2017), no. 4, 1–6.
[2] S. Ali Asghari, F. Ahmadi Abkenar, and A. Shah Bahrami, Identification of systemic and business risks and risk management in customs, Nat. Conf. Organ. Risk Manag., Tehran, Center for Productivity and Human Resources Studies, 2015.
[3] M. Arabi, Strategic Planning of the Customs of the Islamic Republic of Iran, Tehran, Nil Publications, 2004. [In Persian]
[4] J. Biljan and A. Trajkov, Risk management and Customs performance improvements: The case of the Republic of Macedonia, Proc.-Soc. Behav. Sci. 44 (2012), 301–313.
[5] G. Fayyad, P. Piatestsky-Shapiro, and P. Symth, From data mining to knowledge discovery in databases, Al Magazin 17 (1996), 37–54.
[6] W. Gleissner and T. Berger, Einfach Lernen! Risikomanagement, Retrieved November, 2009.
[7] R. Goli, Explanation and Analysis of the Customs Affairs Law and its Executive Regulations, Tehran University Route, 2018.
[8] P. Hanafizadeh, Comparison of two data mining methods in segmenting car body insurance customers based on risk (Case study: Mellat Insurance Company), Ind. Manag. Stud. 30 (2013), 77–97.
[9] M. Hayati, M. Atai, R. Khalokakaei, and A. Sayadi, Risk assessment and ranking in the supply chain using taxonomic analysis method (Case study: Isfahan Steel Complex), J. Operat. Res. Appl. 40 (2013), no. 1, 85–103.
[10] A. Jamaat and F. Asgari, Credit risk management in the banking system with a data mining approach, Quart. J. Quant. Stud. Manag. 11 (2010), 115–126.
[11] H. Jiawei and K. Micheline, Data Mining: Concepts and Techniques, Morgan Kaufmann, 2006.
[12] B. Laporte, Risk management systems: Using data mining in developing countries customs administrations, World Customs J. 5 (2011), no. 1, 17–29.
[13] D.T. Larose and C.D. Larose, Discovering Knowledge in Data: An Introduction to Data Mining, John Wiley & Sons, 2014.
[14] C.V. Martincus, J. Carballo, and A. Graziano, Customs, J. Int. Econ. 96 (2015), 119–137.
[15] Y. Okazaki, Implications of big data for customs -how it can support risk management customs, J. WCO Res. Paper 39 (2017), 1–24.
[16] P. Ravisankar, V. Ravi, G.R. Rao, and I. Bose, Detection of financial statement fraud and feature selection using data mining techniques, Decision Support Syst. 50 (2011), 491–500.
[17] B. Rukanova, Y.-H. Tan, M. Slegt, M. Molenhuis, B.V. Rijnsoever, J. Migeotte, M.L.M. Labare, K. Plecko, B. Caglayan, G. Shorten, O.V.D. Meij, and S. Post, Identifying the value of data analytics in the context of government supervision: Insights from the customs domain, Gover. Inf. Quart. 38 (2021), 101496.
[18] M. Shishechiha, Risk Management in Customs Affairs, Tehran, Basic Science Development Publications, 2015. [In Persian]
[19] M. Yousefi, Comparative Study of Customs Risk Management, Tehran, Dara Publications, 2016. [In Persian]
[20] M. Yousefi, Modern Customs Programs in the 21st Century, Tehran, Dara Publications, 2016. [In Persian]
[21] B.-B. Zehero, E. Soro, Y. Gondo, P. Brou, and O. Asseu, Elicitation of association rules from information on customs offences on the basis of frequent motives, Engineering 10 (2018), no. 9, 588–605.
Volume 15, Issue 7
July 2024
Pages 309-324
  • Receive Date: 13 June 2022
  • Accept Date: 21 August 2022