The Comparison of Artificial Neural Networks and Panel Data Analysis on Profitability Prediction: The Case of Real Estate Investment Trusts

Year 2025, , 160 - 183, 28.03.2025

Ayşegül Peker , Duygu Tunalı

https://doi.org/10.30784/epfad.1602204

Abstract

In recent years, machine learning techniques have come to the forefront for profitability forecasting due to their flexibility in computation, ability to work with large and diverse data types, and capability to predict real-time changes. In addition, predicting profitability in practice is challenging and requires expertise. The primary aim of this study is to determine the most suitable profitability prediction model using Artificial Neural Network (ANN) algorithms, one of the machine learning techniques. Furthermore, the ANN prediction model was applied to the data set for the 2010-2019 quarters created from the financial statements of Real Estate Investment Trusts (REITs) companies traded in Borsa Istanbul (BIST) and the prediction success of the ANN technique was interpreted by comparing the findings obtained with the findings obtained as a result of panel data analysis. The comparison of these values with the findings of the panel data analysis has led to the conclusion that ANN prediction models can make more successful forecasts than panel data analysis models.

Keywords

Profitability Prediction, Artificial Neural Network, Panel Data

Kârlılık Tahmininde Yapay Sinir Ağları ve Panel Veri Analizinin Karşılaştırılması: Gayrimenkul Yatırım Ortaklıkları Örneği

Abstract

Son yıllarda makine öğrenmesi teknikleri, hesaplamadaki esneklikleri, büyük ve çeşitli veri türleriyle çalışabilmeleri ve gerçek zamanlı değişiklikleri tahmin edebilme yetenekleri nedeniyle kârlılık tahmininde ön plana çıkmıştır. Ayrıca uygulamada kârlılığı tahmin etmek zordur ve uzmanlık gerektirir. Bu çalışmanın temel amacı, makine öğrenmesi tekniklerinden biri olan Yapay Sinir Ağları (YSA) algoritmalarını kullanarak en uygun kârlılık tahmin modelini belirlemektir. Ayrıca Borsa İstanbul’da (BİST) işlem gören Gayrimenkul Yatırım Ortaklıkları (GYO) firmalarının mali tablolarından oluşturulan 2010-2019 çeyrek dönemlerine ait veri setine YSA tahmin modeli uygulanmış ve elde edilen bulgular, panel veri analizi uygulanması sonucu elde edilen bulgularla karşılaştırılarak YSA tekniğinin tahmin başarısı yorumlanmıştır. Bu değerlerin yapılan panel veri analizi bulgularıyla karşılaştırılması neticesinde, YSA tahmin modellerinin, panel veri analiz modellerine göre daha başarılı tahmin yapabildiği sonucuna ulaşılmıştır.

Keywords

Karlılık Tahmini, Yapay Sinir Ağı, Panel Veri

References

• Adhikari, R. and Agrawal, R.K. (2013). An introductory study on time series modelling and forecasting. arXiv preprint arXiv:1302.6613. https://doi.org/10.48550/arXiv.1302.6613
• Aktaş, M. and Darwish, Z. (2020). Financial ratios affecting profitability of real estate investment trusts. Finans Ekonomi ve Sosyal Araştırmalar Dergisi, 5(4), 786-794. https://doi.org/10.29106/fesa.827033
• Alaameri, Z.H.O. and Faihan, M.A. (2022). Forecasting the accounting profits of the banks listed in Iraq stock exchange using artificial neural networks. Webology, 19(1), 2669-2682. https://doi.org/10.14704/WEB/V19I1/WEB19177
• Alaloul W.S. and Qureshi A.H. (2020). Data processing using artificial neural networks. In D.G. Harkut (Ed.), Dynamic data assimilation - Beating the uncertainties (pp. 81-106). London: IntechOpen. https://doi.org/10.5772/intechopen.91935
• Anderson, D. and McNeill, G. (1992). Artificial neural networks technology. Kaman Sciences Corporation, 258(6), 1-83. Retrieved from http://www.gaianxaos.com/
• Bakar, N.M.A. and Tahir, I.M. (2009). Applying multiple linear regression and neural network to predict bank performance. International Business Research, 2(4), 176-183. Retrieved from https://pdfs.semanticscholar.org
• Baltagi, B.H. (2005). Econometric analysis of panel data. (3. ed.). Chichester: Wiley.
• Burrell, P.R. and Folarin, B.O. (1997). The impact of neural networks in finance. Neural Computing & Applications, 6(4), 193-200. https://doi.org/10.1007/BF01501506
• Callen, J.L., Kwan, C.C., Yip, P.C. and Yuan, Y. (1996). Neural network forecasting of quarterly accounting earnings. International Journal of Forecasting, 12(4), 475-482. https://doi.org/10.1016/S0169-2070(96)00706-6
• Chai, T. and Draxler, R.R. (2014). Root mean square error (RMSE) or mean absolute error (MAE). Geoscientific Model Development Discussions, 7(1), 1525-1534. https://doi.org/10.5194/gmdd-7-1525-2014
• Coşkuner, A., Rençber, Ö. and Çelik, Z. (2024). The factors that affects the profitability in real estate investment trust companies: Comparison of Turkey and Malaysia. Trends in Business and Economics, 38(1), 2-11. https://doi.org/10.5152/TBE.2023.23108
• Csáji, B.C. (2001). Approximation with artificial neural networks (Unpublished doctoral dissertation). Faculty of Sciences, Eötvös Loránd University, Hungary.
• Cunha, A.M., Borges, A.P. and Ferreira, M. (2024). Do real estate investment companies profit from house price growth? Evidence from Portugal. International Journal of Housing Markets and Analysis, 17(4), 1019-1033. https://doi.org/10.1108/IJHMA-01-2023-0007
• Çelik, E. ve Arslanlı, K. (2020). Gayrimenkul yatırım ortalığı firmalarının piyasa değeri ve aktif kârlılığını etkileyen finansal oranların panel veri analizi yöntemiyle belirlenmesi. Muhasebe ve Finansman Dergisi, 88, 255-274. https://doi.org/10.25095/mufad.801491.
• Da Silva, I.N., Spatti, D.H., Flauzino, R.A., Liboni, L.H.B. and dos Reis Alves, S.F. (2017). Artificial neural network architectures and training processes. In I.N da Silva, D.H. Spatti, R.A. Flauzino, L.H.B. Liboni and S.F. dos R. Alves (Eds.), Artificial neural networks: A practical course (pp. 21-28). Springer, Cham. https://doi.org/10.1007/978-3-319-43162-8
• Desai, V.S. and Bharati, R. (1998). The efficacy of neural networks in predicting returns on stock and bond indices. Decision Sciences, 29(2), 405-423. https://doi.org/10.1111/j.1540-5915.1998.tb01582.x
• Eğrioğlu, E., Yolcu, U. and Baş, E. (2019). Yapay sinir ağları öngörü ve tahmin uygulamaları (2. Bs.). Ankara: Nobel Akademik Yayıncılık.
• Fernandez-Rodriguez, F., Gonzalez-Martel, C. and Sosvilla-Rivero, S. (2000). On the profitability of technical trading rules based on artificial neural networks: Evidence from the Madrid stock market. Economics Letters, 69(1), 89-94. https://doi.org/10.1016/S0165-1765(00)00270-6
• Heo, W., Lee, J.M., Park, N. and Grable, J.E. (2020). Using artificial neural network techniques to improve the description and prediction of household financial ratios. Journal of Behavioral and Experimental Finance, 25, 100273. https://doi.org/10.1016/j.jbef.2020.100273
• Ho, D.C.K., Chan, E.M.H., Yip, T.L. and Tsang, C.W. (2020). The United States’ clothing imports from Asian countries along the Belt and Road: An extended gravity trade model with application of artificial neural network. Sustainability, 12(18), 7433. https://doi.org/10.3390/su12187433
• Hsiao, C. (2014). Analysis of panel data (3nd ed.). New York: Cambridge University Press.
• Jakpar, S., Tinggi, M., Tak, A.H. and Ruzlan, N.A. (2018). Determinant factors of profitability in Malaysia’s real estate investment trusts (M-REITS). UNIMAS Review of Accounting and Finance, 2(1), 72-84. https://doi.org/10.33736/uraf.1209.2018
• Khalil, D.M. (2022). A comparison of time series and artificial neural network models for forecasting turkey's monthly agricultural exports to Iraq (Unpublished doctoral dissertation). Kahramanmaraş Sütçü İmam University, Kahramnamaraş, Türkiye.
• Kıral, G. and Çelik, C. (2020). Panel verileri ile Türkiye’de konut fiyatlarını etkileyen faktörlerin tespiti ve yapay sinir ağları yaklaşımı. Çankırı Karatekin Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 11(2), 1-21. Retrieved from https://dergipark.org.tr/en/pub/jiss
• Kröse, B. and Smagt, P. (1996). An introduction to neural networks. (8nd ed.). Amsterdam: The University of Amsterdam.
• Kukreja, H., Bharath, N., Siddesh, C.S. and Kuldeep, S. (2016). An introduction to the artificial neural network. International Journal of Advance Research and Innovative Ideas in Education, 1, 27-30. Retrieved from https://www.ijariie.com
• Lado-Sestayo, R. and Vivel-Búa, M. (2020). Hotel profitability: A multilayer neural network approach. Journal of Hospitality and Tourism Technology, 11(1), 35-48. https://doi.org/10.1108/JHTT-08-2017-0072
• Marak, Z.R., Ambarkhane, D. and Kulkarni, A.J. (2022). Application of artificial neural network model in predicting profitability of Indian banks. International Journal of Knowledge-based and Intelligent Engineering Systems, 26(3), 159-173. https://doi.org/10.3233/KES-220020
• Min, J. (2020). Financial market trend forecasting and performance analysis using LSTM. arXiv preprint arXiv:2004.01502. https://doi.org/10.48550/arXiv.2004.01502
• Mohamad, H.H., Ibrahim, A.H. and Massoud, H.H. (2013). Assessment of the expected construction company’s net profit using neural network and multiple regression models. Ain Shams Engineering Journal, 4(3), 375-385. https://doi.org/10.1016/j.asej.2012.11.008
• Monteiro, M. and Costa, M. (2018). A time series model comparison for monitoring and forecasting water quality variables. Hydrology, 5(3), 37. https://doi.org/10.3390/hydrology5030037
• Ocakdan, P. (2019). Türkiye'deki gayrimenkul yatırım ortaklıklarının karlılık analizi (Yayımlanmamış doktora tezi). İstanbul Aydın Üniversitesi Sosyal Bilimler Enstitüsü, İstanbul.
• Olson, D. and Mossman, C. (2003). Neural network forecasts of Canadian stock returns using accounting ratios. International Journal of Forecasting, 19(3), 453-465. https://doi.org/10.1016/S0169-2070(02)00058-4
• Ömürbek, V., Akçakanat, Ö. and Aksoy, E. (2019). Aktif büyüklüklerine göre değerlendirilen büyük ölçekli bankaların yapay sinir ağları ile kârlılık tahmini. Atatürk Üniversitesi İktisadi ve İdari Bilimler Dergisi, 33(2), 451-466. Retrieved from https://dergipark.org.tr/tr/pub/trendbusecon
• Öndeş, T. and Barakalı, O.C. (2023). Faiz oranlarının gayrimenkul yatırım ortaklığı karlılık oranları üzerinde etkisi. Muhasebe ve Finansman Dergisi, 97, 49-62. https://doi.org/10.25095/mufad.1184115
• Öztemel, E. (2020). Yapay sinir ağları. (5. Bs.). İstanbul: Papatya Yayıncılık Eğitim.
• Parlakkaya, R.P., Kahraman, Ü. and Cihan, Y. (2022). Katılım bankaları ile geleneksel bankaların sermaye yapılarının karşılaştırılması: Türk bankacılık sektörü üzerine bir uygulama. Akademik Yaklaşımlar Dergisi, 13(2), 479-504. https://doi.org/10.54688/ayd.1109005
• Pesaran, M.H. (2007). A simple panel unit root test in the presence of cross‐section dependence. Journal of Applied Econometrics, 22(2), 265-312. https://doi.org/10.1002/jae.951
• Saberi, M., Rostami, M. R., Hamidian, M. and Aghami, N. (2016). Forecasting the profitability in the firms listed in Tehran Stock Exchange using data envelopment analysis and artificial neural network. Advances in Mathematical Finance and Applications, 1(2), 95-104. Retrieved from https://www.ensani.ir/
• Schöneburg, E. (1990). Stock price prediction using neural networks: A project report. Neurocomputing, 2(1), 17-27. https://doi.org/10.1016/0925-2312(90)90013-H
• Shanmuganathan, S. (2016). Artificial neural network modelling: An introduction. In S. Shanmuganathan and S. Samarasinghe (Eds.), Artificial neural network modelling (pp. 1-14). Berlin: Springer.
• Sharma, V., Rai, S. and Dev, A. (2012). A comprehensive study of artificial neural networks. International Journal of Advanced Research in Computer Science and Software Engineering, 2(10), 278-284. Retrieved from https://:www.ijarcsse.com
• Sönmez, F., Zontul, M. and Bülbül, Ş. (2015). Mevduat bankalarının kârlılığının yapay sinir ağları ile tahmini: Bir yazılım modeli tasarımı. BDDK Bankacılık ve Finansal Piyasalar Dergisi, 9(1), 9-46. Retrieved from https://dergipark.org.tr/tr/pub/bddkdergisi
• Tatoğlu, Y.F. (2021). Panel veri ekonometrisi Stata uygulamalı. (6. Bs.). İstanbul: Beta Yayıncılık.
• Tekin, B. (2021). The factors affecting the market value/book value and profitability of REITs in Turkey. International Real Estate Review, 24(3), 469-499. Retrieved from https://papers.ssrn.com/
• Vukovic, D.B., Spitsina, L., Gribanova, E., Spitsin, V. and Lyzin, I. (2023). Predicting the performance of retail market firms: Regression and machine learning methods. Mathematics, 11(8), 1916. https://doi.org/10.3390/math11081916
• Yavuz, S. and Deveci, M. (2012). İstatiksel normalizasyon tekniklerinin yapay sinir ağın performansına etkisi. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 40, 167-187. Retrieved from https://dergipark.org.tr/en/pub/erciyesiibd