MAKİNE ÖĞRENMESİ İLE ULUSLARARASI MUHASEBEDE ERTELENMİŞ VERGİLERİN TAHMİNLEMESİ

Year 2022, , 1303 - 1326, 29.07.2022

Feden Koç , Ahmet Çağdaş Seçkin , Osman Bayri

https://doi.org/10.30798/makuiibf.1034685

Abstract

Bu çalışmanın amacı, hisse senetleri Borsa İstanbul (BIST)'da toptan ticaret, perakende ticaret ve konaklama sektörü olmak üzere üç farklı sektörde işlem gören 31 şirketin muhtemel ertelenmiş vergi değerlerini ve TMS-TFRS kar /zararını tahmin etmektir. Bu tahmin, şirketlerin 2015-2019 yılları için ertelenmiş vergi değerlerine ve on iki temel ekonomik parametreye dayanmaktadır. Çalışma kapsamında, şirketlerin 2020 yılında yıllık finansal raporlarında sunacakları ertelenmiş vergi çıktı parametreleri aşağıdaki yöntemler kullanılarak tahmin edilmiştir: 0,823 doğruluk oranı ile random forest yöntemi kullanılarak ertelenmiş vergi varlığı değeri, 0,790 doğruluk oranına sahip yapay sinir ağları yöntemi kullanılarak net ertelenmiş vergi varlığı değeri, 0,823 doğruluk oranı ile random forest yöntemi kullanılarak ertelenmiş vergi yükümlülüğü değeri ve 0,887 doğruluk oranı ile random forest yöntemi kullanılarak net ertelenmiş vergi yükümlülüğü değeri. Ayrıca, çıktı parametrelerinden olan TMS-TFRS kar / zarar değerinin 0,629 doğruluk oranı ile random forest yöntemi kullanılarak tahmin edilebileceği belirlenmiştir.

Keywords

International Accounting Standards-International Financial Reporting Standards (IAS-IFRS), Turkish Accounting Standards- Turkish Financial Reporting Standards (TAS-TFRS), Valuation, Deffered Taxes, Machine Learning, Artifical Neural Networks.

FORECASTING DEFERRED TAXES IN INTERNATIONAL ACCOUNTING WITH MACHINE LEARNING

Abstract

The aim of this study is to estimate the possible deferred tax values and the TAS-TFRS profit/loss of 31 companies in three different sectors- the wholesale trade, retail trade and hospitality industry- whose shares are traded on Borsa Istanbul (BIST). This estimation is based on the companies' deferred tax values for the years 2015-2019 as well as twelve main economic parameters. Within the context of the study, the deferred tax output parameters, which companies will present in their annual financial reports in 2020, have been estimated using the following methods: the DTA value using the random forest method with an accuracy rate of 0,823, the net DTA value using the artificial neural networks method with an accuracy rate of 0,790, the DTL value using the random forest method with an accuracy rate of 0,823 and the net DTL value using the random forest method with an accuracy rate of 0,887. In addition, it has been discovered that the TAS-TFRS profit/loss, which is one of the output parameters, can be estimated using the random forest method with an accuracy rate of 0,629.

Keywords

International Accounting Standards-International Financial Reporting Standards (IAS-IFRS), Turkish Accounting Standards- Turkish Financial Reporting Standards (TAS-TFRS), Valuation, Deffered Taxes, Machine Learning, Artifical Neural Networks.

References

• Abraham, M. (2019). Studying The Patterns and Long-Run Dynamics İn Cryptocurrency Prices. Journal of Corporate Accounting & Finance, 21(3), 1-2. doi: 10.1002/jcaf.22427.
• Alpaydın, E. (2009). Introduction to Machine Learning. (4. Edition). Cambridge/Massachusetts: MIT press.
• Altman, N. S. (1992). An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. The American Statistician, 46(3), 175–85. doi: 10.2307/2685209.
• Altunöz. U. (2013). Prediction of Financial Failure of Banks by Artifical Neural Network Model. Dokuz Eylul University Faculty of Economics and Administrative Sciences Journal, 28(2), 189.
• Anderson, D. and George M. (1992). Artificial Neural Networks Technology. Data & Analysis Center for Software (DACS) State-of-the-Art Report. ELIN: A011. New York: Kaman Sciences Corporation, New York.
• Treasury and Finance Ministry, Economic İndicators, Turkey, (2020, 14 July), https://ms.hmb.gov.tr/uploads/2020/04/aylikekonomikgosterge01042020.pdf.
• Balcıoğlu, H. E., Seçkin A. Ç. and Aktaş M. (2015). Failure Load Prediction of Adhesively Bonded Pultruded Composites Using Artificial Neural Network, Journal of Composite Materials, 50(23), 3267-3281. doi: 10.1177/0021998315617998.
• Bateni, L. and Farshid A. (2020). Bankruptcy Prediction Using Logit and Genetic Algorithm Models: A Comparative Analysis. Computational Economics, 55(1), 335–48. doi: 10.1007/s10614-016-9590-3.
• Breiman, L. (2001). Random Forests. Machine Learning 45(1), 5-32. doi: 10.1023/A:1010933404324 .
• Çelik, O. (2014). Deferred taxes and turkey with sample application access to financial reporting standards, Ankara: Certified Public Accountant and Turkey Union of Chambers of Certified Public Accountants, (1. Edition). (TURMOB) Publications-465.
• Detienne, K. B., David H. D. ve Shirish A. J. (2003). Neural Networks as Statistical Tools for Business Researchers. Organizational Research Methods, 6(2), 240.
• Ding, K. B. L., Xuan P., Ting S., and Miklos A. V. (2020). Machine Learning Improves Accounting Estimates. SSRN Scholarly Paper. ID 3253220. Rochester, NY: Social Science Research Network.
• Etheridge, H. L., Sriram, R. S. and Hsu. H. Y. K. (2007). A Comparison of Selected Artificial Neural Networks that Help Auditors Evaluate Client Financial Viability. A Joural Of The Decision Sciences Instıtute, 31(2): 531. doi: 10.1111/j.1540-5915.2000.tb01633.x.
• Fadlalla, A. and Amani. F. (2014). Predicting Next Trading Day Closing Price Of Qatar Exchange Index Using Technical Indicators and Artificial Neural Networks. İntelligent Systems in Accounting, Finance and Management, 21(4), 209-223. doi: 10.1002/isaf.1358.
• Freund, Y. and Robert E. S. (1997). A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting, Journal of Computer and System Sciences, 55(1), 119-39. doi: 10.1006/jcss.1997.1504.
• Gaeremynck, A. and L. Van De G. (2004). The Recognition and Timing of Deferred Tax Liabilities. Journal of Business Finance & Accounting, 31(7‐8), 985–1014. doi: 10.1111/j.0306-686X.2004.00564.x.
• Gupta, S. and Kashyap, S. (2015). S. Forecasting İnflation in G-7 Countries: An Application of Artificial Neural Network. Foresight, 17(1), 63. doi: 10.1108/FS-09-2013-0045. Hosaka, T. (2019). Bankruptcy Prediction Using İmaged Financial Ratios and Convolutional Neural Networks. Expert Systems with Applications, (117), 287, doi: 10.1016/j.eswa.2018.09.039.
• İnstitutions Tax Law, (2006). Vol. 5520. https://www.mevzuat.gov.tr/MevzuatMetin/1.5.5520.pdf
• James, G., Daniela W., Trevor H. and Robert T. (2013). An Introduction to Statistical Learning. (2th ed.). with Applications in R, Springer.
• Public Oversight Accounting and Auditing Standards Authority (KGK) TMS 12 İncome Taxes. https://kgk.gov.tr/Portalv2Uploads/files/DynamicContentFiles/T%C3%BCrkiye%20Muhasebe%20Standartlar%C4%B1/TMSTFRS2017Seti/3-TMS/TMS_12_2017.pdf
• Karakaya G. and Sevim C. (2016). The concept of deferred tax according to accounting standard of income taxes (TMS-12) and an Application. Journal Of Accounting, Finance And Auditing Studies (Jafas), 2(3), 257.
• Koç, F. (2018). The evaluation of financial reporting of value added tax based receivables within the framework of effect analysis on taxable and accounting profit. Doctoral thesis. Suleyman Demirel University.
• Kohavi, R. (1995). Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. Appears in the International Joint (IJCA), (14),1137-1145.
• Küçük, E. (2014). The evaluation of financial reporting of value added tax based receivables within the framework of effect analysis on taxable and accounting profit, Journal of Management and Economics Research, (24), 300. doi: 10.11611/JMER496.
• Kumar, K. and Sukanto, B. (2006). Artificial Neural Network vs Linear Discriminant Analysis in Credit Ratings Forecast: A Comparative Study of Prediction Performances. Review of Accounting and Finance, 5(3), 216-27. doi: 10.1108/14757700610686426.
• León, C., José F. M. and Jorge C. (2017). Whose Balance Sheet Is This? Neural Networks for Banks’ Pattern Recognition. Wilmott (91), 34. Maint, S.B. and Wankar, P. (2014). Research Paper on Basic of Artificial Neural Network, International Journal on Recent and Innovation Trends in Computing and Communication, 2(1), 96-100.
• Maiti, M., Yaroslav V. and Darko V. (2020, 6 August). Cryptocurrencies Chaotic Co‐movement Forecasting With Neural Networks. İnternet Technology Letter. https://doi.org/10.1002/itl2.157
• Masand, B., Gordon L. and David W. (1992). Classifying News Stories Using Memory Based Reasoning. in Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval, SIGIR ’92. (59-65 ss.). Copenhagen, Denmark: Association for Computing Machinery. doi: 10.1145/133160.133177.
• Mohammadi, M., Shohreh Y., Mohammad Hamed K. ve Keyhan M. (2020). Financial Reporting Fraud Detection: An Analysis of Data Mining Algorithms. International Journal of Finance & Managerial Accounting, 4(16), 1-12.
• Omar, N., Johari, Z. A. and Smith. M. (2017). Predicting Fraudulent Financial Reporting Using Artificial Neural Network. Journal of Financial Crime 24(2), 362. doi: 10.1108/JFC-11-2015-0061.
• Oxner, K. M., Thomas H. O. and A. D. P. (2018). Impact Of The Tax Cuts and Jobs Act on Accounting For Deferred Income Taxes. Journal of Corporate Accounting & Finance, 29(2), 13-14. doi: 10.1002/jcaf.22339.
• Özkan, A. (2009). Deferred taxes and their accounting applications in compliance with accounting standard of income taxes (TMS-12). Erciyes University Economics and Administrative Science Faculty Journal, (32), 99-105. Persio, L. D. and Honchar, O. (2016). Artificial Neural Networks Approach to the Forecast of Stock Market Price Movements. International Journal of Economics and Management Systems, (1),158-162.
• Seçkin, A. Ç. and Aysun C. (2019). Hierarchical Fusion of Machine Learning Algorithms in Indoor Positioning and Localization. Applied Sciences, 9(18), 2-16. doi: 10.3390/app9183665.
• Seçkin, M., Ahmet Ç. S. and Aysun C. (2019). Production Fault Simulation and Forecasting from Time Series Data with Machine Learning in Glove Textile Industry. Journal of Engineered Fibers and Fabrics, (14), 6-7. doi: 10.1177/1558925019883462.
• Singh, N., Lai, K., Vejvar, M. and Cheng, T. C. E. (2019). Data-Driven Auditing: A Predictive Modeling Approach to Fraud Detection and Classification. Journal of Corporate Accounting and Finance, 3(30), 64. doi: 10.1002/jcaf.22389.
• Sun, T. ve Vasarhelyi, M. A. (2018). Predicting credit card delinquencies: An application of deep neural networks. Intelligent Systems in Accounting, Finance and Management, 25(4), 174-189. doi: 10.1002/isaf.1437.
• Vochozka, M. (2018). Comparison of Neural Networks and Regression Time Series in Estimating the Development of the Afternoon Price of Palladium on the New York Stock Exchange. Trends Economics and Management, 30(3), 73–83. doi: 10.13164/trends.2017.30.73.