Türkiye’de Tüketici Fiyat Endeksi Tahmini: Derin Öğrenme ve Makine Öğrenme Yaklaşımlarının Karşılaştırılması

Year 2024, Issue: 36, 312 - 344, 31.05.2024

Yunus Emre Gür

https://doi.org/10.54600/igdirsosbilder.1386274

Abstract

Bu çalışma, 2005 Ocak – 2023 Haziran dönemine ait aylık tüketici fiyat endeksi verileri ve 5 adet bağımsız değişken (İşsizlik Oranı, Ortalama Dolar Kuru, Üretici Fiyat Endeksi, Brent Petrol Fiyatları, İhtiyaç Kredisi Faiz Oranı) verilerini kullanarak derin öğrenme ve makine öğrenme algoritmalarının Tüketici Fiyat Endeksi (TÜFE) tahmini üzerindeki etkinliğini araştırmayı amaçlamaktadır. Bu doğrultuda, TÜFE tahmini için, Uzun ve Kısa Süreli Bellek, Geçitli Tekrarlayan Birim, Rastgele Orman, Yapay Sinir Ağı ve K-En Yakın Komşular gibi farklı derin öğrenme ve makine öğrenme modelleri kullanılmış ve tahmin performansları değerlendirilmiştir.
Sonuçlar, Geçitli Tekrarlayan Birim modelinin Uzun ve Kısa Süreli Hafıza, Rastgele Orman, Yapay Sinir Ağı ve K-En Yakın Komşular modellerinden daha başarılı olduğunu göstermiştir. Diğer dört modele kıyasla, Geçitli Tekrarlayan Birim modelinde RMSE, MSE, MAE, MAPE ve R^2 değerleri daha iyi performans göstermiştir. Ek olarak, Tüketici Fiyat Endeksi tahmininde, enflasyon alanında derin öğrenme ve makine öğrenme modellerinin etkin bir şekilde kullanılabileceği gözlemlenmiştir. Bu sonuçlar, ekonomik tahminlerin ve enflasyonun yönetilmesinin önemli bir bileşeni olan TÜFE tahmininde etkili bir yol sunmaktadır. Akademik açıdan, bu çalışma, derin öğrenme ve makine öğrenme modellerinin ekonomi ve finans alanında uygulanabilirliğini göstermektedir. Uygulamada, ekonomik ve finansal karar alıcıları için değerli bir araç sunmaktadır.

Keywords

Tüketici Fiyat Endeksi Tahmini, Derin Öğrenme, Makine Öğrenimi, Geçitli Tekrarlayan Birim

Ethical Statement

Çalışma için etik kurul izni almaya gerek duyulmamıştır.

Consumer Price Index Forecasting in Turkey: A Comparison of Deep Learning and Machine Learning Approaches

Abstract

Accordingly, different deep learning and machine learning models such as long- and short-term memory, temporal recurrent units, random forests, artificial neural networks, and K-nearest neighbors are used for CPI forecasting. The prediction performances of the models on the test data were evaluated with RMSE, MSE, MAE, MAPE, and R^2 error statistics.
The results show that the Gateway Recurrent Unit model outperforms the Long and Short Term Memory, Random Forest, Neural Network, and K-Nearest Neighbors models. Compared to the other four models, the RMSE, MSE, MAE, MAPE, and R^2 values performed better in the recurrent unit model. In addition, it has been observed that deep learning and machine learning models can be used effectively in the field of inflation in consumer price index forecasting. These results provide an effective method of CPI forecasting, which is an important component of economic forecasting and inflation management. From an academic perspective, this study demonstrates the applicability of deep learning and machine learning models in economics and finance. In practice, it provides a valuable tool for economic and financial decision-makers and illuminates the way for future similar studies.

Keywords

Inflation Forecasting, Deep Learning, Machine Learning, Gated Recurrent Unit

References

• Abraham, A. (2005). Artificial neural networks. Handbook of Measuring System Design, edited by Peter H. Sydenham and Richard Thorn, John Wiley & Sons, Ltd. ISBN: 0-470-02143-8.
• Alkaff, M., Mustamin, N. F., & Firdaus, G. A. A. (2022). Prediction of crime rate in Banjarmasin City using RNN-GRU model. International Journal of Intelligent Systems and Applications in Engineering, 10(3), 01-09.
• Altunöz, U. (2022). The nonlinear and asymetric pass‐through effect of crude oil prices on inflation. OPEC Energy Review, 46(1), 31-46. https://doi.org/10.1111/opec.12221
• Azam, R., Muhammad, D., & Akbar, S. S. (2012). The significance of socioeconomic factors on personal loan decision (a study of consumer banking in local private banks in pakistan). SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2167960
• Basher, S. A. & Sadorsky, P. (2022). Forecasting Bitcoin price direction with random forests: How important are interest rates, inflation, and market volatility?. Machine Learning with Applications, 9, 100355.
• Bayramoğlu, A. T. & Öztürk, Z. (2017). Inflation forecasting with ARIMA and gray system models. Journal of Human and Social Sciences Research, 6(2), 760-776.
• Bhat, M. R., Jiao, J., & Azimian, A. (2021). The impact of covid-19 on home value in major texas cities. International Journal of Housing Markets and Analysis, 16(3), 616-627. https://doi.org/10.1108/ijhma-05-2021-0058
• Boaretto, G. & Medeiros, M. C. (2023). Forecasting inflation using disaggregates and machine learning. arXiv preprint arXiv:2308.11173.
• Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
• Cheung, K. L. & Fu, A.W. C. (1998), Enhanced nearest neighbor search on the R-tree. ACM SIGMOD Record 27(3), 16– 21.
• Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H. & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation, arXiv preprint arXiv:1406.1078, https://doi.org/10.48550/arXiv.1406.1078.
• Cuñado, J. & Gracia, F. P. d. (2005). Oil prices, economic activity and inflation: evidence for some asian countries. The Quarterly Review of Economics and Finance, 45(1), 65-83. https://doi.org/10.1016/j.qref.2004.02.003
• Da Silva, I. N., Hernane Spatti, D., Andrade Flauzino, R., Liboni, L. H. B., dos Reis Alves, S. F., da Silva, I. N., ... & dos Reis Alves, S. F. (2017). Artificial neural network architectures and training processes (pp. 21-28). Springer International Publishing.
• Dhanabal, S., & Chandramathi, S. J. I. J. C. A. (2011). A review of various k-nearest neighbor query processing techniques. International Journal of Computer Applications, 31(7), 14-22.
• Erdem, H. F. & Yamak, R. (2014). The degree of pass-through between the producer price index and the consumer price index. Anadolu University Journal of Social Sciences, 14(4), 1-13.
• Firdauza, D. N. & Rahadian, Y. (2022). Determining factors of financial performance recovery in bri during the covid-19 pandemic. Economics Development Analysis Journal, 11(1), 49-60. https://doi.org/10.15294/edaj.v11i1.52990
• Ganzagh, H. A., Samimi, A. J., Elmi, Z. M. & Tehranchian, A. M. (2023). Comparing Inflation Forecasting Models in Iran: New Evidences from ARDL-D-LSTM Model. Iranian Journal of Economic Research, 27(93), 149-176.
• Gao, Y., Wang, R. & Zhou, E. (2021). Stock Prediction Based on Optimized LSTM and GRU Models. Scientific Programming, 2021. https://doi.org/10.1155/2021/4055281
• Gharaibeh, A. M. O. & Farooq, M. O. (2022). Determinants of bank lending rates: empirical evidence from conventional retail banks in bahrain. Banks and Bank Systems, 17(4), 140-153. https://doi.org/10.21511/bbs.17(4).2022.12
• Gritli, M. I. (2021). Price inflation and exchange rate pass‐through in tunisia. African Development Review, 33(4), 715-728. https://doi.org/10.1111/1467-8268.12599
• Haryono, A. T., Sarno, R. & Sungkono, K. R. (2023). Transformer-Gated Recurrent Unit Method for Predicting Stock Price based on News Sentiments and Technical Indicators. IEEE Access.
• Hatipoğlu, Ş., Belgrat, M. A., Degirmenci, A., & Karal, Ö. (2021). Prediction of Unemployment Rates in Turkey by k-Nearest Neighbor Regression Analysis. In 2021 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-5). IEEE.
• Helmy, O., Fayed, M. M. S., & Hussien, K. (2018). Exchange rate pass-through to inflation in egypt: a structural var approach. Review of Economics and Political Science, 3(2), 2-19. https://doi.org/10.1108/reps-07-2018-001
• Henrich, A. (1994). A distance scan algorithm for spatial access structures. In: Proceedings of the Second ACM Workshop on Geographic Information Systems, pp. 136– 143.
• Hjaltason, G.R., & Samet, H. (1999). Distance browsing in spatial databases. ACM Trans. Database Sys. 24(2), 265–318.
• Hsing, Y. (2020). A simultaneous-equation model of estimating the response of the consumer price to exchange rate movements in thailand. Business and Economic Research, 10(1), 284. https://doi.org/10.5296/ber.v10i1.16406
• Işığıçok, E., Öz, R., & Tarkun, S. (2020). Forecasting and technical comparison of inflation in Turkey with box-jenkins (ARIMA) models and the artificial neural network. International Journal of Energy Optimization and Engineering (IJEOE), 9(4), 84-103.
• Jang, P. Y. & Beruvides, M. G. (2020). Time-varying influences of oil-producing countries on global oil price. Energies, 13(6), 1404. https://doi.org/10.3390/en13061404
• Jamil, H. (2022). Inflation forecasting using hybrid ARIMA-LSTM model (Doctoral dissertation, Laurentian University of Sudbury).
• Khan, A., Kandel, J., Tayara, H., & Chong, K. T. (2024). Predicting the bandgap and efficiency of perovskite solar cells using machine learning methods. Molecular Informatics, 43(2). https://doi.org/10.1002/minf.202300217
• Kubheka, S. (2023). South African inflation modelling using bootstrapped long short-term memory methods. SN Business & Economics, 3(7), 110.
• Kitani, R. & Iwata, S. (2023). Verification of interpretability of phase-resolved partial discharge using a cnn with shap. IEEE Access, 11, 4752-4762. https://doi.org/10.1109/access.2023.3236315
• Kosztowniak, A. (2022). Credit policy of commercial banks in eu and the asset quality of non-financial corporate loan portfolio in 2009-2021. European Research Studies Journal, XXV(Issue 1), 563-582. https://doi.org/10.35808/ersj/2871
• Lee, K., Ayyasamy, M. V., Ji, Y., & Balachandran, P. V. (2022). A comparison of explainable artificial intelligence methods in the phase classification of multi-principal element alloys. Scientific Reports, 12(1). https://doi.org/10.1038/s41598-022-15618-4
• Li, S., Huang, H., & Lu, W. (2021). A neural networks based method for multivariate time-series forecasting. IEEE Access, 9, 63915-63924. https://doi.org/10.1109/access.2021.3075063
• Lin, Y. & Thompson, H. (2020). Exchange rate pass-through to consumer prices: the increasing role of energy prices. Open Economies Review, 32(2), 395-415. https://doi.org/10.1007/s11079-020-09601-7
• Nguyen, T. T., Nguyen, H. G., Lee, J. Y., Wang, Y. L., & Tsai, C. S. (2023). The consumer price index prediction using machine learning approaches: Evidence from the United States. Heliyon, 9(10).
• Öniş, Z. & Özmucur, S. (1987), Inflation in Turkey, Istanbul: ITO Publication No: 1987-5.
• Rodríguez-Vargas, A. (2020). Forecasting Costa Rican inflation with machine learning methods. Latin American Journal of Central Banking, 1(1–4), 100012. https://doi.org/10.1016/j.latcb.2020.100012.
• Rodríguez-Pérez, R. & Bajorath, J. (2020). Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. Journal of Computer-Aided Molecular Design, 34(10), 1013-1026. https://doi.org/10.1007/s10822-020-00314-0
• Sakashita, Y. & Yoshizaki, Y. (2016). The effects of oil price shocks on iip and cpi in emerging countries. Economies, 4(4), 20. https://doi.org/10.3390/economies4040020
• Savitri, F. F., Siregar, R. F., Harianto, F. Y. & Napitupulu, H. (2021). Forecasting Inflation in Indonesia using Long Short Term Memory. In 2021 International Conference on Artificial Intelligence and Big Data Analytics (pp. 43-49). IEEE.
• Saqib, A., Yasmin, F., & Hussain, I. (2023). Does the crime rate respond symmetrically or asymmetrically to changes in governance quality and macroeconomic variables? the application of linear and non-linear ardl. International Journal of Social Economics, 50(12), 1756-1776. https://doi.org/10.1108/ijse-09-2022-0625
• Schröder, M. and Hüfner, F. (2002). Exchange rate pass-through to consumer prices: a european perspective. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.304939
• Sek, S. K. (2019). Effect of oil price pass-through on domestic price inflation: evidence from nonlinear ardl models. Panoeconomicus, 66(1), 69-91. https://doi.org/10.2298/pan160511021s
• Serrano‐Cinca, C., Nieto, B. G., & López-Palacios, L. (2015). Determinants of default in p2p lending. Plos One, 10(10), e0139427. https://doi.org/10.1371/journal.pone.0139427
• Sevgen, S. C. & Aliefendioğlu, Y. (2020). Mass Apprasial With A Machine Learning Algorithm: Random Forest Regression. Bilişim Teknolojileri Dergisi, 13(3), 301-311.
• Soylu, Ö. B., Çakmak, İ., & Okur, F. (2018). Economic growth and unemployment issue: panel data analysis in eastern european countries. Journal of International Studies, 11(1), 93-107. https://doi.org/10.14254/2071-8330.2018/11-1/7
• Sun, Q., Wang, Z., & Jia, N. (2022). Revisiting the dynamic response of chinese price level to crude oil price shocks based on a network analysis method. Entropy, 24(7), 944. https://doi.org/10.3390/e24070944
• The Central Bank of the Republic of Turkey, https://evds2.tcmb.gov.tr/ Access Date: 04.07.2023
• Tunalı, H. & Özkan, İ. (2016). An Empirical Analysis of the Relationship between Consumer Confidence Index and Consumer Price Index in Turkey. Journal of Economic Policy Researches, 3(2), 54-67.
• Usupbeyli, A. and Uçak, S. (2020). The effects of exchange rates on cpi and ppi. Business and Economics Research Journal, 11(2), 323-334. https://doi.org/10.20409/berj.2020.252
• Xu, W., Zhang, J., Zhang, Q. & Wei, X. (2017). Risk prediction of type II diabetes based on random forest model. Proceedings of the 3rd IEEE International Conference on Advances in Electrical and Electronics, Information, Communication and Bio-Informatics, AEEICB 2017, 382–386. https://doi.org/10.1109/AEEICB.2017.7972337
• Yang, C. & Guo, S. (2021). Inflation prediction method based on deep learning. Computational Intelligence and Neuroscience, 2021.
• Yu, C. D., Huang, J., Austin, W., Xiao, B., & Biros, G. (2015). Performance optimization for the k-nearest neighbors kernel on x86 architectures. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (pp. 1-12).