Veri Madenciliği Süreci ile Türkiye'de Vergi Kayıp ve Kaçakların Tahmini

Vergi kayıp ve kaçakları tüm dünyada olduğu gibi ülkemizde de en büyük sorunlardan biridir. Denetimlerin yanı sıra, istatistiksel teknikler ve makine öğrenimi algoritmaları da vergi kayıp ve kaçaklarının tespitinde büyük önem taşımaktadır. Bu çalışmada vergi kayıp ve kaçak oranı; enflasyon oranı, işsizlik, vergi yükü, cari açık, ekonomik büyüme (GSYİH), devletin büyüklüğü gibi faktörlere bağlı olarak veri madenciliği süreci ile tahmin edilmiştir. Veri madenciliği sürecinde on iki modelleme tekniği kullanılmıştır. Her modelden elde edilen sonuçlar karşılaştırılmış ve bazı istatistiksel göstergeler kullanılarak en iyi model belirlenmiştir. Buna göre, vergi kayıp ve kaçak oranı tahmininde en başarılı sonucu R2, MAE ve RMSE değerleri sırasıyla 0,931, 0,2356 ve 0,2473 olan Gaussian processes modeli vermiştir. Vergi kayıp ve kaçak oranını etkileyen değişkenlerin ağırlık değerleri duyarlılık analizi ile belirlenmiştir. Vergi kayıp ve kaçaklarında pozitif etkisi en yüksek olan faktörlerin işsizlik ve enflasyon oranları olduğu görülmüştür. Bu faktörleri vergi yükü ve GSYİH değerleri izlemektedir. Devletin büyüklüğü ve cari açık faktörlerinin ise vergi kayıp ve kaçak oranı üzerinde negatif etkiye sahip olduğu görülmüştür. Çalışmadan elde edilen sonuçların ülkemizdeki vergi kayıp ve kaçak oranının tahmin edilmesine katkı sağlayacağı düşünülmektedir.

Anahtar Kelimeler:

Vergi kaybı, Vergi kaçağı, Veri madenciliği

Estimation of Tax Loss and Evasion in Turkey with Data Mining Process

Tax losses and evasion are one of the biggest problems in our country as well as all over the world. In addition to audits, statistical techniques and machine learning algorithms are also of great importance in detecting tax losses and evasion. In this study, the tax loss and evasion rate has been estimated by the data mining process depending on factors such as inflation rate, unemployment, tax burden, trade openness, economic growth (GDP), and the size of government. Twelve modeling techniques were used in the data mining process. The results obtained from each model were compared and the best model was determined using some statistical indicators. Accordingly, the Gaussian processes model gave the most successful result in estimating tax loss and evasion rate, with R2, MAE and RMSE values of 0.931, 0.2356 and 0.2473, respectively. The weight values of the variables affecting the tax loss and evasion rate were determined by sensitivity analysis. It has been observed that the factors with the highest positive effect on tax losses and evasion are unemployment and inflation rates. These factors are followed by tax burden and GDP values. It was seen that the size of government and the trade openness factors had a negative effect on the tax loss and evasion rate. It is thought that the results obtained from the study will contribute to the estimation of the tax loss and evasion rate in our country.

Keywords:

Tax loss, Tax evasion, Data mining,

PDF

___

Albarea, A., Bernasconi, M., Marenzi, A., & Rizzi, D. (2020). “Income underreporting and tax evasion in Italy: Estimates and distributional effects”. Review of Income and Wealth, 66(4), 904-930.
Amoh, J. K., & Adafula, B. (2019). “An estimation of the underground economy and tax evasion: Empirical analysis from an emerging economy”. Journal of Money Laundering Control.
Angour, N., & Nmili, M. (2019). “Estimating shadow economy and tax evasion: Evidence from Morocco”. International Journal of Economics and Finance, 11(5), 1-7.
Armağan, A. (2016). Yargı Kararları Işığında Türkiye’de Vergi Kayıp ve Kaçakları ile Mücadele ve Alternatif Çözüm Arayışları. Doktora Tezi, Süleyman Demirel Üniversitesi Sosyal Bilimler Enstitüsü, Isparta.
Athanasios, A., Eleni, K., & Charalampos, K. (2020). “Estimation of the size of tax evasion in Greece”. Bulletin of Applied Economics, 7(2), 97.
Ay, A. , Sugözü, İ. H. & Erdoğan, S. (2014). “Türkiye’de Vergi Yükünün, Enflasyonun ve Vergi Affı Beklentisinin Kayıt Dışı Ekonomiye Etkisi Üzerine Ampirik Bir Uygulama 1985-2012”. Selçuk Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, (31.1) , 23-32.
Besley, T., & Persson, T. (2009). “The origins of state capacity: Property rights, taxation, and politics”. American Economic Review, 99(4), 1218-44.
Caballé, J., & Panadés, J. (2004). “Inflation, tax evasion, and the distribution of consumption”. Journal of Macroeconomics, 26(4), 567-595.
Çomakli, Ş. E. (2008). “AB İlerleme Raporlari Çerçevesinde Türkiye’deki Vergi Kayip ve Kaçaklarinin Önlenmesine Yönelik Uygulamalar”. Atatürk Üniversitesi İktisadi ve İdari Bilimler Dergisi, 22(1), 51-82.
D’Agostino, E., De Benedetto, M. A., & Sobbrio, G. (2021). “Tax evasion and government size: evidence from Italian provinces”. Economia Politica, 38(3), 1149-1187.
Dang, S. K., & Singh, K. (2021). “Predicting tensile-shear strength of nugget using M5P model tree and random forest: An analysis”. Computers in Industry, 124, 103345.
Dell’Anno, R., Gómez, M., & Pardo, Á. A. (2004). “Shadow Economy in Three Very Different Mediterranean Countries: France, Spain and Greece”. A Mimic Approach. CRISS, http://www. unisi. it/criss/download/meeting2004/papers/dellanno. pdf.
Dell'Anno, R. (2007). “The shadow economy in Portugal: An analysis with the MIMIC approach”. Journal of Applied Economics, 10(2), 253-277.
Dell’Anno, R., & Davidescu, A. A. (2019). “Estimating shadow economy and tax evasion in Romania. A comparison by different estimation approaches”. Economic Analysis and Policy, 63, 130-149.
Demircan, E.S. (2004). “Türkiye'de Vergi Politikalarının Siyasi Analizi: Siyasi Değişimin Vergi Kayıp ve Kaçaklarına Etkisi Üzerine Bir İnceleme”, 19. Türkiye Maliye Sempozyumu, 10-14 Mayıs 2004, Belek/Antalya.
Faúndez-Ugalde, A., Mellado-Silva, R., & Aldunate-Lizana, E. (2020). “Use of artificial intelligence by tax administrations: An analysis regarding taxpayers’ rights in Latin American countries”. Computer Law & Security Review, 38, 105441.
Gao, W., Alsarraf, J., Moayedi, H., Shahsavar, A., & Nguyen, H. (2019). “Comprehensive preference learning and feature validity for designing energy-efficient residential buildings using machine learning paradigms”. Applied Soft Computing, 84, 105748.
George-Nektarios, T. (2013). Weka classifiers summary. Athens University of Economics and Bussiness Intracom-Telecom, Athens.
Gerçek, A., Uygun, E. (2022). “Türkiye’de Vergi Kayıp ve Kaçakların Vergi Türlerine Göre Hesaplanması ve Değerlendirilmesi (2005-2020 Yılları)”, Vergi Raporu Dergisi, 268, (163-177).
Hemberg, E., Rosen, J., Warner, G., Wijesinghe, S., & O’Reilly, U. M. (2016). “Detecting tax evasion: a co-evolutionary approach”. Artificial Intelligence and Law, 24(2), 149-182.
Khosravi, K., Khozani, Z. S., & Cooper, J. R. (2021). “Predicting stable gravel-bed river hydraulic geometry: A test of novel, advanced, hybrid data mining algorithms”. Environmental Modelling & Software, 144, 105165.
Kirmanoğlu, H. (2007). Kamu Ekonomisi Analizi, Beta Yayınevi, İstanbul.
Levin, J., & Widell, L. M. (2014). “Tax evasion in Kenya and Tanzania: Evidence from missing imports”. Economic Modelling, 39, 151-162.
Li, L., & Ma, G. (2015).” Government Size and Tax Evasion: Evidence from China”. Pacific Economic Review, 20(2), 346-364.
Madžarević-Šujster, S. (2002). “An estimate of tax evasion in Croatia”. Occasional paper series, 6(13), 1-23.
Mishra, S. 2004. Sensitivity analysis with correlated inputs—An environmental risk assessment example. In Proceedings of the 2004 Crystal Ball User Conference.
Niranjan, A., Nutan, D. H., Nitish, A., Shenoy, P. D., & Venugopal, K. R. (2018, April). ERCR TV: Ensemble of random committee and random tree for efficient anomaly classification using voting. In 2018 3rd international conference for convergence in technology (I2CT) (pp. 1-5). IEEE.
Petanlar, S. K., Samimi, A. J., & Aminkhaki, A. (2011). “An Estimation of Tax Evasion in Iran”. Journal of Economics and Behavioral Studies, 3(1), 8-12.
Rahimikia, E., Mohammadi, S., Rahmani, T., & Ghazanfari, M. (2017). “Detecting corporate tax evasion using a hybrid intelligent system: A case study of Iran”. International Journal of Accounting Information Systems, 25, 1-17.
Rajalakshmi, A., Vinodhini, R., & Bibi, K. F. (2016). “Data Discretization Technique Using WEKA Tool”. International Journal of Science, Engineering and Computer Technology, 6(8), 293.
Raikov, A. (2021). “Decreasing tax evasion by artificial intelligence”. IFAC-PapersOnLine, 54(13), 172-177.
Sandalci, U., Sandalci, İ. (2016). “Kamu Kesimi Ekonomik Büyüklüğü ve Kamu Etkinlik Düzeyi İlişkisi”. Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, (Ek1), 413-429.
Sameti, M.A. &Sameti, M.O. & Dalaeemillan, A. (2009). “Underground Economy in Iran”. International Economics Studies of Iran, 35 (2), 89-114.
Savaşan, F. (2003). “Modeling the underground economy in Turkey: randomized response and MIMIC models”. The Journal of Economics, 29(1), 49-76.
Schneider, F., & Savasan, F. (2007). “Dymimic estimates of the size of shadow economies of Turkey and of her neighbouring countries”. International Research Journal of Finance and Economics, 9(5), 126-143.
Seeger, M. (2004). “Gaussian processes for machine learning”. International Journal of Neural Systems, 14(02), 69-106.
Shakil, M. H., & Tasnia, M. (2022). “Artificial Intelligence and Tax Administration in Asia and the Pacific”. In Taxation in the Digital Economy (pp. 45-55). Routledge.
Shevade, S. K., Keerthi, S. S., Bhattacharyya, C., & Murthy, K. R. K. (2000). “Improvements to the SMO algorithm for SVM regression”. IEEE transactions on neural networks, 11(5), 1188-1193.
Sritharan, N., & Salawati, S. (2019). “Economic factors impact on individual taxpayers’ tax compliance behaviour in Malaysia”. Int. J. Acad. Res. Account. Finance. Manag. Sci, 9, 172-182.
Tabandeh, R., Jusoh, M., Nor, N. G. M., & Zaidi, M. A. S. (2012). “Estimating factors affecting tax evasion in Malaysia: A neural network method analysis”. Prosiding Persidangan Kebangsaan Ekonomi Malaysia Ke VII, 1525.
Tabandeh, R., & Tamadonnejad, A. (2015). “The application of artificial neural network method to investigate the effect of unemployment on tax evasion”. Journal of Research in Business, Economics and Management, 4(3), 393-402.
Ture, M., Kurt, I., Kurum, A. T., & Ozdamar, K. (2005). “Comparing classification techniques for predicting essential hypertension”. Expert Systems with Applications, 29(3), 583-588.
Turkish Statistical Institute (TÜİK). (2022). https://www.tuik.gov.tr/
T.R. Presidential Strategy and Budget Department (2022). https://www.sbb.gov.tr
Uyar, A., Bani-Mustafa, A., Nimer, K., Schneider, F., & Hasnaoui, A. (2021). “Does innovation capacity reduce tax evasion? Moderating effect of intellectual property rights”. Technological Forecasting and Social Change, 173, 121125.
Van Dunem, J. E., & Arndt, C. (2009). “Estimating border tax evasion in Mozambique”. The Journal of Development Studies, 45(6), 1010-1025.
Warner, G., Wijesinghe, S., Marques, U., Badar, O., Rosen, J., Hemberg, E., & O’Reilly, U. M. (2015). “Modeling tax evasion with genetic algorithms”. Economics of Governance, 16(2), 165-178.
WEKA 3.9 software, https://waikato.github.io/weka-wiki/downloading_weka/ Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., (2005, June). “Practical machine learning tools and techniques”. In Data Mining (Vol. 2, No. 4).
Xiangyu, X., Youlin, Y., & Qicheng, X. (2018, July). Intelligent Identification of Corporate Tax Evasion Based on LM Neural Network. In 2018 37th Chinese Control Conference (CCC) (pp. 4507-4511). IEEE.
Zou, K. H., Tuncali, K., & Silverman, S. G. (2003). “Correlation and simple linear regression”. Radiology, 227(3), 617-628.
Zumaya, M., Guerrero, R., Islas, E., Pineda, O., Gershenson, C., Iñiguez, G., & Pineda, C. (2021). “Identifying tax evasion in Mexico with tools from network science and machine learning”. In Corruption Networks (pp. 89-113). Springer, Cham.