Forecasting Unemployment Rate in the Aftermath of the Covid-19 Pandemic: The Turkish Case

Yıl 2021, Cilt: 36 Sayı: 3, 685 - 693, 02.09.2021

Mustafa Batuhan Tufaner , İlyas Sözen

https://doi.org/10.24988/ije.202136312

Cited By: 2

Öz

The coronavirus (Covid-19) pandemic caused the loss of lives, global problems, and the collapse of economies. Especially, the high unemployment rates in developing countries at present makes the unemployment rate predictions important. The aim of this study is to estimate the unemployment rate for the future by ARIMA and Artificial Neural Networks (ANN) models for Turkey. The contribution of the study to the literature is to estimate the unemployment rate in Turkey in the aftermath of the Covid-19 by ARIMA and ANN models. In the study, the Box-Jenkins method was used to find the appropriate ARIMA process. Then, the estimated performance of the results obtained up to 2021M8 unemployment rates in Turkey have been compared in the framework of criteria for success. Our results show that ANN was more successful than the ARIMA model in estimating the unemployment variable. It seemed that the unemployment rate estimated by the model is very close to the actual unemployment rate. According to the model results, in the aftermath of Covid-19, the unemployment rate in Turkey will be occurred over 5% of the natural rate of unemployment.

Anahtar Kelimeler

Covid-19, Unemployment, Artificial Neural Networks, ARIMA, Turkey

Covid-19 Salgını Sonrası İşsizlik Oranının Tahmini: Türkiye Örneği

Öz

Koronavirüs (Covid-19) salgını can kaybına, küresel sorunlara ve ekonomilerin çökmesine neden olmuştur. Özellikle gelişmekte olan ülkelerdeki yüksek işsizlik oranları, işsizlik oranı tahminlerini önemli hale getirmektedir. Çalışmanın amacı, Türkiye için ARIMA ve Yapay Sinir Ağları (YSA) modelleri ile geleceğe yönelik işsizlik oranını tahmin etmektir. Çalışmanın literatüre katkısı, Covid-19 sonrasında Türkiye'deki işsizlik oranını ARIMA ve YSA modelleri ile tahmin etmektir. Çalışmada, uygun ARIMA sürecini bulmak için Box-Jenkins yöntemi kullanılmıştır. Ardından, Türkiye'de 2021M8 dönemine kadar işsizlik oranlarından elde edilen sonuçların tahmini performansı kriterlere göre karşılaştırılmıştır. Bulgular, YSA'nın işsizlik değişkenini tahmin etmede ARIMA modelinden daha başarılı olduğunu göstermektedir. Model tarafından tahmin edilen işsizlik oranının gerçek işsizlik oranına oldukça yakın olduğu görülmüştür. Model sonuçlarına göre Covid-19 sonrasında Türkiye'deki işsizlik oranı doğal işsizlik oranı olan % 5'in üzerinde gerçekleşecektir.

Anahtar Kelimeler

Covid-19, İşsizlik, Yapay Sinir Ağları, ARIMA, Türkiye

Kaynakça

• Akgul, I. (2003). Zaman serilerinin analizi ve arima modelleri. İstanbul: Der Yayınevi.
• Bod’a, M. and Považanová, M. (2021). Output-unemployment asymmetry in Okun coefficients for OECD countries. Economic Analysis and Policy, 69, 307-323.
• Chakraborty, T., Chakraborty, A., Biswas, M., Banerjee, S. and Bhattacharya, S. (2020). Unemployment rate forecasting: a hybrid approach. Computational Economics, 1-19.
• Chen, X., Racine, J. and Swanson, N. (2001). Semiparametric arx neural network models with an application to forecasting inflation. IEEE Transactions on Neural Networks, 12, 674–683.
• Choudhary, M. A. and Haider, A. (2012). Neural network models for inflation forecasting: an appraisal. Applied Economics, 44, 2631-2635.
• Chuku C., Odour J. and Simpasa A. (2017). Intelligent forecasting of economic growth for African economies: artificial neural networks versus time series and structural econometric models. Forecasting Issues in Developing Economies 2017 conference paper. Washington.
• Coredo, E. and Cabrera-Sanchez, J. P. (2020). Private label and macroeconomic indexes: an artificial neural networks application. Applied Science, 10(17), 1-13.
• Dumičić, K., Čeh Časni, A. and Žmuk, B. (2015). Forecasting unemployment rate in selected European countries using smoothing methods. World Academy of Science, Engineering and Technology: International Journal of Social, Education, Economics and Management Engineering, 9, 867–872.
• Edlund, P. O. and Karlsson, S. (1993). Forecasting the Swedish unemployment rate VAR vs. transfer function modelling. International Journal of Forecasting, 9, 61–76.
• Falat, L. and Pancikova, L. (2015). Quantitative modelling in economics with advanced artificial neural networks. Procedia Economics and Finance, 34, 194-201.
• Faraway, J. and Chatfield, C. (1998). Time series forecasting with neural networks: a comparative study using the airline data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 47, 231–250.
• Fausett, L. (1994). Fundamentals of neural networks: architecture, algorithms and applications, New Jersey: Prentice Hall.
• Fenga, L. and Turan, S. S. (2020). Forecasting youth unemployment in the aftermath of the covid-19 pandemic: the Italian case. Research Square, DOI: 10.21203/rs.3.rs-74374/v1.
• Feuerriegel, S. and Gordon, J. (2019). News-based forecasts of macroeconomic indicators: a semantic path model for interpretable predictions. European Journal of Operational Research, 272, 162–175.
• Funke, M. (1992). Time-series forecasting of the German unemployment rate. Journal of Forecasting, 11, 111–125.
• Gujarati, D. N. (2004). Basic econometrics, Fourth Edition, The McGraw-Hill Inc.
• Hamzacebi, C. (2011). Yapay sinir ağları: tahmin amaçlı kullanımı Matlab ve Neurosolutions uygulamalı, Bursa: Ekin Yayıncılık.
• Herbrich, R., Graepel, T. and Obermayer, K. (1999). Regression models for ordinal data: a machine learning approach, Technical report, TU Berlin. TR-99/03.
• Huang, W., Lai, K. K., Nakamori, Y., Wang, S. and Yu, L. (2007). Neural networks in finance and economics forecasting. International Journal of Information Technology and Decision Making, 6, 113-140.
• Jalaee, S. A., Lashkary, M. and GhasemiNejad, A. (2019). The Phillips curve in Iran: econometric versus artificial neural networks. Heliyon, 5, 1-6.
• Johnes, G. (1999). Forecasting unemployment. Applied Economics Letters, 6, 605-607.
• Katris, C. (2019). Prediction of unemployment rates with time series and machine learning techniques. Computational Economics, 55, 673-706.
• Khan-Jaffur, Z. R., Sookia, N. U. H., Nunkoo Gonpot, P. and Seetanah, B. (2017). Out-of-sample forecasting of the Canadian unemployment rates using univariate models. Applied Economics Letters, 24, 1097–1101.
• Kizilkaya, O. (2017). Türkiye’nin enflasyon ve işsizlik oranının yapay sinir ağları ve Box-Jenkins yöntemiyle tahmini. Social Sciences Studies Journal, 3, 2197-2207.
• Liliana, Napitupulu, T. A. (2012). Artificial neural network application in gross domestic product forecasting an Indonesia case. Journal of Theoretical and Applied Information Technology, 45, 410-415.
• Nagao, S., Takeda, F. and Tanaka, R. (2019). Nowcasting of the US unemployment rate using google trends. Finance Research Letters, 30, 103–109.
• Nakamura, E. (2005). Inflation forecasting using a neural network. Economics Letter, 86, 373-378.
• Proietti, T. (2003). Forecasting the US unemployment rate. Computational Statistics and Data Analysis, 42, 451–476.
• Popescu M. C., Olaru, O. and Mastorakis, N. (2009). Equilibrium dynamic systems integration proceedings of the 10th WSEAS, Int. Conf. on Automation & Information, Prague, 424- 430.
• Refenes, A. P. and White, H. (1998). Neural networks and financial economics, International Journal of Forecasting, 6.
• Sengul, G. and Tasci, M. (2020). Unemployment flows, participation, and the natural rate of unemployment: evidence from Turkey. Journal of Macroeconomics, 64(C), 1-14.
• Sermpinis, G., Stasinakis, C., Theofilatos, K. and Karathanasopoulos, A. (2014). Inflation and unemployment forecasting with genetic support vector regression. Journal of Forecasting, 33, 471-487.
• Soybilgen, B. and Yazgan, E. (2018). Nowcasting the new Turkish gdp. Economics Bulletin, 38, 1083-1089.
• Teräsvirta, T., Van Dijk, D. and Medeiros, M. C. (2005). Linear models, smooth transition autoregressions, and neural networks for forecasting macroeconomic time Series: a re-examination. International Journal of Forecasting, 21, 755–774.
• Thomas R. C. and Hall, A. S. (2017). Macroeconomic indicator forecasting with deep neural networks. Research Working Paper RWP, 17-11.
• Tkacz G. (2001). Neural network forecasting of Canadian gdp growth. International Journal of Forecasting, 17, 57-69.
• Vicente, M. R., López-Menéndez, A. J. and Pérez, R. (2015). Forecasting unemployment with internet search data: does it help to improve predictions when job destruction is skyrocketing?. Technological Forecasting and Social Change, 92, 132–139.
• Wozniak, M. (2020). Forecasting the unemployment rate over districts with the use of distinct methods. Studies in Nonlinear Dynamics & Econometrics, De Gruyter, 24, 1-20.
• Zhang, G., Patuwo, B. E. and Hu, M. Y. (1998). Forecasting with artificial neural networks: the state of the art. International Journal of Forecasting, 14, 35-62.