کاربست الگوریتم های یادگیری ماشین در پیش بینی انتظارات تورمی با استفاده از متغیرهای اقتصادی و پولی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری اقتصاد، گروه اقتصاد، دانشکده مدیریت و اقتصاد، دانشگاه آزاد اسلامی واحد ابرکوه، یزد، ایران

2 استادیار، گروه اقتصاد، دانشکده مدیریت و اقتصاد، دانشگاه آزاد اسلامی واحد یزد، یزد، ایران

3 دانشیار، گروه اقتصاد، دانشکده مدیریت و اقتصاد، دانشگاه آزاد اسلامی واحد یزد، یزد، ایران

چکیده

ارائه پیش‌بینی‌های قابل اعتماد انتظارات تورمی چالشی همیشگی برای سیاست‌گذاران است و برای فعالان اقتصادی و تصمیم‌های سرمایه‌گذاری آنها از اهمیت بالایی برخوردار است. پیش‌بینی دقیق انتظارات تورمی در یک محیط غنی از داده زمانی که بین متغیرهای پیش بینی کننده همبستگی وجود دارد یک زمینه تحقیقاتی فعال است. هدف این پژوهش پیش بینی انتظارات تورمی با درنظرگرفتن متغیرهای اقتصادی و پولی با بهره گیری از الگوریتم های یادگیری ماشین جهت کمک به تصمیم گیری سیاست گذاران اقتصادی کشور است. دلیل انتخاب روش یادگیری ماشین برای پیش بینی انتظارات تورمی، نداشتن مشکلات ساختاری مدل های تحلیلی و توانایی تشخیص دقیق روند بین معیارها در محیط اقتصادی غنی از داده است. برای دستیابی به این هدف داده های نرخ رشد اقتصادی، شاخص قیمت واردات، شاخص قیمت تولید کننده، سطح شکاف تولید، ارقام بودجه و تراز پرداخت‌ها، نرخ رشد دستمزد، رشد نقدینگی، نرخ ارز، درآمدهای نفتی، شاخص‌ بازار سهام، نرخ‌ بهره برای بازه زمانی از ابتدای سال 1384 تا انتهای سال 1398 جمع آوری گردید. یافته ها نشان داد که الگوریتم لاسوی تطبیق یافته نسبت به الگوریتم های دیگر یادگیری ماشین دارای عملکرد بهتری در پیش بینی انتظارات تورمی است. همچنین نتایج نشان داد که نرخ ارز و رشد نقدینگی به عنوان متغیرهای اقتصادی و نرخ بهره به عنوان متغیر پولی توانایی بالاتری در پیش بینی انتظارات تورمی دارند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

The machine learning algorithms usage in predicting inflation expectations by using economic and monetary variables

نویسندگان [English]

  • Zahra Mokhtari 1
  • Jalil Totonchi 2
  • Abbas Alavi Rad 3
1 Ph.D. Candidate, Department of Economics, Faculty of Management and Economics, Islamic Azad University of Abarkouh, Yazd, Iran
2 Assistant Professor, Department of Economics, Faculty of Management and Economics, Islamic Azad University Yazd, Yazd, Iran
3 Associate Professor, Department of Economics, Faculty of Management and Economics, Islamic Azad University Yazd, Yazd, Iran
چکیده [English]

Purpose: Providing reliable forecasts of inflation expectations is a constant challenge for policymakers, and it is of vital for economic activists and their investment decisions. Accurate forecasting of inflation expectations in a data-rich environment when there is a correlation among predictor variables is an active research field. The purpose of this study is to predict inflation expectations by considering economic and monetary variables using machine learning algorithms to help the economic policy makers of the country.

Methodology: In this study, machine learning algorithms are used to select the most effective variables in predicting inflation expectations. This procedure is suitable for discovering complex patterns, and it is based on fewer and more restrictive assumptions. For this purpose, the data are grouped into two sets of training and testing, and a 14-year period is considered for training sets. The model prediction accuracy is evaluated in the 15th year. The variables include exchange rate, stock market index, balance of payments, production price index, import price index, wage growth rate, production gap, economic growth rate, money market interest rate, liquidity growth, and oil revenues. Forecasting inflation expectations is done using the ridge, lasso, adaptive lasso and elastic net algorithms. Also, the mean square error criterion is used to check the machine the accuracy of learning techniques.

Findings and Discussion: The findings of this research showed that, in the adaptive lasso algorithm, there is a smaller difference between the observed and estimated values than in the other techniques of predicting inflation expectations. The mean square error for the real and estimated values in the adaptive Lasso algorithm is 0.0892. The results confirmed that the oracle feature of the adaptive lasso algorithm was able to reduce the penalty by giving less weight to them and leave their effects in the model in a real form. Based on this, among economic variables, exchange rate and liquidity growth have the most positive effects on inflation expectations. Their coefficients are 3.144 and 2.904, respectively. Also, the interest rate as a monetary variable has the most negative effect on inflation expectations with a coefficient of -4.383. This result is in line with Fisher's theory because Fisher believed that a higher interest rate leads to a decrease in inflation, and an increase in the interest rate can reduce the consumption attractiveness and demand.
 
Conclusions and Policy Implications: The difference between the amounts of import and export in Iran causes a high dependence on the import of goods, and any change in the exchange rate helps to form the consumer expectations regarding future inflation. Also, the process of creating liquidity without support due to the lack of coordination at the level of goods production and services causes inflation expectations. The central bank can encourage people to deposit their savings in banks by increasing the deposit interest rate. On the one hand, the demand decreases and, on the other hand, the total consumption and the money circulation slow down. Considering the results of this research, policymakers and economic officials can directly apply machine learning algorithms to the problem of macroeconomic forecasting in a data-rich environment, using all the corresponding predictors without the need for multivariate linear modeling and with minimal errors.
Keywords: Forecasting inflation expectations, Learning machine, Exchange rate, Liquidity, Interest rate

کلیدواژه‌ها [English]

  • forecasting inflation expectations
  • learning machine
  • exchange rate
  • liquidity
  • interest rate

مراجع

Aboulhassani, A., Shaygani, B. & Zandian, Z. (2020). The Effect of Interest Rate and Exchange Rate on Inflation Targeting with Heterogeneous Inflation Expectations Approach. Journal of Econometric Modelling, 5(1): 87-110. Doi: 10.22075/jem.2020.18166.1338. (In Persian)
Ascari, G., Fasani, S., Grazzini, J. & Rossi, L. (2023). Endogenous Uncertainty and the Macroeconomic Impact of Shocks to Inflation Expectations. Journal of Monetary Economics, 140: 48-63. https://doi.org/10.1016/j.jmoneco.2023.04.002.
Badel, A. & McGillicuddy, J. (2015). Oil Prices and Inflation Expectations: Is There a Link? The Regional Economist: Federal Reserve Bank of St. Louis.
Bottone, M. & Rosolia, A. (2019). Monetary Policy, Firms’ Inflation Expectations and Prices: Causal Evidence from Firm-Level Data. Working Papers 1218: Bank of Italy
Coibion, O., Gorodnichenko, Y. & Ropele, T. (2020). Inflation Expectations and Firm Decisions: New Causal Evidence. The Quarterly Journal of Economics, 135(1): 165–219. https://doi.org/10.1093/qje/qjz029.
De Carvalho, A. R., Ribeiro, R. S. M. & Marques, A. M. (2018). Economic Development and Inflation: A Theoretical and Empirical Analysis. International Review of Applied Economics, 32(4): 546-565. https://doi.org/10.1080/02692171.2017.1351531.
Djalo, M. U., Yusuf, M., & Pudjowati, J. (2023). The Impact of Foreign Debt on Export and Import Values, the Rupih Exchange Rate, and the Inflation Rate. Jurnal Ekonomi, 12(01): 1124–1132.
Dogan, I., Orun, E., Aydın, B. & Saban Afsal, M. (2020). Non-Parametric Analysis of the Relationship between Inflation and Interest Rate in the Context of Fisher Effect for Turkish Economy. International Review of Applied Economics, 34(6): 758-768. https://doi.org/10.1080/02692171.2020.1782852.
Dupor, B. & Li, R. (2015). The Expected Inflation Channel of Government Spending in the Postwar U.S. European Economic Review, 74, 36-56. https://doi.org/10.1016/j.euroecorev.2014.11.004.
Farrokhi Balajadeh, H., Khochiani, R. & Asayesh, H. (2019). Investigating the Dynamic Relationship between the Money Growth and Inflation in Iran: An Econophysics Analysis of Quantity Theory of Money. Quarterly Journal of Applied Theories of Economics, 6(2): 215-238. (In Persian)
Frache, S. & Lluberas, R. (2018). New Information and Inflation Expectations among Firms. Working Paper 781: Bank for International Settlements.
Galindo, A. J. & Steiner, R. (2022). Asymmetric Interest Rate Transmission in an Inflation-Targeting Framework: The Case of Colombia. Latin American Journal of Central Banking, 3(3): 1-18.
Goyal, A. & Parab, P. M. (2019). Modeling Consumers' Confidence and Inflation Expectations. Economics Bulletin, 39(3): 1817-1832.
Güler, A. (2021). Does Monetary Policy Credibility Help in Anchoring Inflation Expectations? Evidence from Six Inflation Targeting Emerging Economies. Journal of Central Banking Theory and Practice, 10(1): 93-111. https://doi.org/10.2478/jcbtp-2021-0005.
Hassanvand, D. & Nademi, Y. (2018). Empirical Analysis of Existence of the Mundell's Relationship between Interest Rate and Inflation in Iran: A State-Space Approach. Monetary & Financial Economics, 25(15): 219-238. Doi: 10.22067/pm.v25i16.63738 (In Persian)
Istiak, K. & Alam, M.R. (2019). Oil Prices, Policy Uncertainty and Asymmetries in Inflation Expectations. Journal of Economic Studies, 46(2): 324-334. https://doi.org/10.1108/JES-02-2018-0074.
Khodabakhshi, A., Akbari Moghadam, B., & Bidabad, B. (2021). Investigating the Nonlinear Effect of Interest Rates on the General Level of Prices, Smooth Transition Regression Approach. Quarterly Journal of Applied Theories of Economics, 8(2): 267-294. Doi: 10.22034/ecoj.2021.43669.2801. (In Persian)
Kilian, L. & Zhou, X. (2022). Oil Prices, Gasoline Prices, and Inflation Expectations. Journal of Applied Econometrics, 37(5): 867–881. https://doi.org/10.1002/jae.2911.
Kotchoni, R., Leroux, M. & Stevanovic, D. (2019). Macroeconomic Forecast Accuracy in a Data-Rich Environment. Journal of Applied Econometrics, 34(7): 1050-1072. https://doi.org/10.1002/jae.2725.
Lipka, A., Nowacka, D. & Rzeszutek, A. (2022). The Evolution of Public Debt, Gross Domestic Product and Inflation Rate in Poland in 2015-2021. Olsztyn Economic Journal, 17(1): 23–33. https://doi.org/10.31648/oej.8600.
Liu, H. & Zhang, J. (2009). Estimation Consistency of the Group Lasso and its Applications. J Mach Learn Res Workshop Conf Proc, 5(3): 76–83.
Madadpour, S. & Asgari, M. (2019). The Puzzling Relationship between Stocks Return and Inflation: a Review Article. Int Rev Econ, 66(1): 115–145.
Medeiros, M.C., Vasconcelos, G. & Freitas, E. (2016). Forecasting Brazilian Inflation with Highdimensional Models. Brazilian Review of Econometrics, 36(2): 223-254.
Moessner, R. (2022). Determinants of Inflation Expectations in the Euro Area. Intereconomics, 57(2), 99–102.
Mokhtari, Z., Totonchi, J. & Alavi Rad, A. (2022). A New Keynesian Approach to Exchange Rate Substitutability in Inflation Expectations: A Dynamic Stochastic General Equilibrium Model. Journal of Applied Economics, 12(41): 91-105. (In Persian)
Nachane, D.M. & Chaubal, A. (2023). Machine Learning in Macroeconomics: Application to DSGE Models. In: Srivastava, D.K., Shanmugam, K.R. (eds) India’s Contemporary Macroeconomic Themes. India Studies in Business and Economics, 521-541. https://doi.org/10.1007/978-981-99-5728-6_22.
Nasir, M. A., Balsalobre-Lorente, D. & Duc Huynh, T. L (2020). Anchoring Inflation Expectations in the Face of Oil Shocks & in the Proximity of ZLB: A Tale of Two Targeters. Energy Economics, 86: 1-13.
Nasir, M. A., Duc Huynh, T. L. & Vinh Vo, X. (2020). Exchange Rate Pass-Through & Management of Inflation Expectations in a Small Open inflation targeting economy. International Review of Economics & Finance, 69: 178-188. https://doi.org/10.1016/j.iref.2020.04.010.
Nasir, M. A. & Duc Huynh, T. L. (2024). Nexus between Inflation and Inflation Expectations at the Zero Lower Bound: A Tiger by the Tail. Economic Modelling, 131, 106601. https://doi.org/10.1016/j.econmod.2023.106601.
Ndikumana, L. (2016). Causes and Effects of Capital Flight from Africa: Lessons from Case Studies. African Development Review, 28(2): 2-7. https://doi.org/10.1111/1467-8268.12177.
Orlowski, L. T. & Soper, C. (2019). Market Risk and Market-Implied Inflation Expectations. International Review of Financial Analysis, 66(1): 1-32. https://doi.org/10.1016/j.irfa.2019.101389.
Özer, M., Zoran, G. & Sevilay, K. (2023). Effects of Exchange Rate, Output Gap, and Output Gap Volatility on Inflation Volatility in Turkey. Journal of Central Banking Theory and Practice, 12(1): 5-26. https://doi.org/10.2478/jcbtp-2023-0001.
Özgür, Ö. & Akkoç, U. (2022). Inflation Forecasting in an Emerging Economy: Selecting Variables with Machine Learning algorithms. International Journal of Emerging Markets, 17(8): 1889-1908. https://doi.org/10.1108/IJOEM-05-2020-0577. 
Ponticelli, J. & Voth, H. J. (2020). Austerity and Anarchy: Budget Cuts and Social Unrest in Europe, 1919–2008. Journal of Comparative Economics 48(1), 1-19. https://doi.org/10.1016/j.jce.2019.09.007.
Saboori Deylami, M. H., Elahi, N., Kiaalhoseini, S. Z. A. & Yousefi Sheikh Robaat, M. (2021). Existence of Exchange Rate-Inflation Vicious Circle Hypothesis in Iran: A MSBVAR Approach. The Journal of Economic Studies and Policies, 8(1): 7-30. https://doi.org/10.22096/esp.2019.37179. (In Persian)
Samsami, H., Orooji, Z. & Dashtban Farooji, S. (2023). Investigating the Effects of Exchange Rate Change on the Trade Balance: The Generalized Marshall-Lerner Condition Approach to in Accordance with the Conditions of Iran's Economy. New Economy and Trade, 18(1): 123-146. Doi: 10.30465/jnet.2023.41152.1886. (In Persian)
Şen, H., Kaya, A., Kaptan, S. & Cömert, M. (2020). Interest Rates, Inflation, and Exchange Rates in Fragile EMEs: A Fresh Look at the Long-Run Interrelationships. The Journal of International Trade & Economic Development an International and Comparative Review, 29(3): 289-318. https://doi.org/10.1080/09638199.2019.1663441.
Shakeri Bostanabad, R., Rasouli Beirami. Z., Salehi Komrudi, M., & Pakrooh, P. (2020). The Impact of Expectations, Liquidity Surplus and Demand Side on Inflation Dynamics in Iran: Hybrid New Keynesian Phillips Curve Approach. Journal of Islamic Economics and Banking, 9(31): 147-171. (In Persian)
Sousa, R. & Yetman, J. (2016). Inflation Expectations and Monetary Policy. Bank for International Settlements. Available at SSRN: https://ssrn.com/abstract=2870936.
Storm, S. (2021). Cordon of Conformity: Why DSGE Models Are Not the Future of Macroeconomics. International Journal of Political Economy, 50(2): 77-98.  https://doi.org/10.1080/08911916.2021.1929582.
Tahsili, H. (2022). The Impact of Exchange Rate Shock on Inflation in Iran's Economy: Application of the Threshold Vector Autoregression Model. Iranian Journal of Economic Research, 27(91): 257-285. Doi: 10.22054/ijer.2022.56063.912. (In Persian)
Uddin, I. & Rahman, K.U. (2023). Impact of Corruption, Unemployment and Inflation on Economic Growth Evidence from Developing Countries. Qual Quant, 57(1): 2759–2779.
Vernengo, M. & Perry, N. (2018). Exchange Rate Depreciation, Wage Resistance and Inflation in Argentina (1882–2009). Economic Notes, 47(1): 125-144. https://doi.org/10.1111/ecno.12098.
Zhang, Ch., Liu, Zh., Xu, Y. & Zhang, Y. (2022). How Do Firms form Inflation Expectations? Empirical Evidence from the United States. Economic Research-Ekonomska Istraživanja, 35(1): 1142-1161. https://doi.org/10.1080/1331677X.2021.1958245.
سیاست گذاری اقتصادی
دوره 18، شماره 35
فروردین 1405
صفحه 182-210

فایل ها

هم رسانی

ارجاع به این مقاله

آمار