Print
№4 (29) / 2025  

Release Date 10.11.2025

 FROM THEORY TO ECONOMIC POLICY

 

 

Shcherbakov Vasilii

PhD (Economy), head of economic department

The Ural Main Branch of the Central Bank of the Russian Federation (Ekaterinburg);

associate professor

Faculty of Economics, Psychology, Management, Dostoevsky Omsk State University (Omsk), This email address is being protected from spambots. You need JavaScript enabled to view it.

https://orcid.org/0000-0001-5132-7423

 

ASSESSMENT OF INFLATION EXPECTATIONS OF THE RUSSIAN POPULATION BASED ON INTERNET SEARCH QUERIES (TOP-DOWN APPROACH)

Размер файла68-90 Размер файла  3.1 М Размер файла Text of the Article   License Creative Commons 4.0 

By their nature, inflation expectations are an unobservable variable. In the framework of economic theory and practice, proxy indicators of inflation expectations (mainly based on surveys) are used as the most important variables for analyzing and forecasting inflationary processes. At the same time, when implementing the inflation targeting regime, regulators primarily focus on managing inflation expectations through monetary policy communications. In this respect, their special, dual character is manifested. Today, the use of alternative estimates of inflation expectations, including search query statistics, continues to grow in popularity. The selection of keywords for quantifying the expectations of the population remains a conceptual issue. The purpose of the study is to develop a methodologically sound approach to selecting keywords for search queries, statistics on which can be used as proxy variables of inflationary expectations. Within the framework of the article, this goal is achieved on the basis of text analysis of communications of the Bank of Russia using machine learning models (especially NLP). Based on the frequency analysis (Baseline approach), as well as the use of advanced NLP models (the T5 family of models ("Text-to-Text Transfer Transformer"), four groups of keywords ("inflation", "Central Bank", "exchange rate", "key rate") were identified using which the regulator can shape the inflation expectations of the Russian population (top-down approach). Due to recent changes in the policy of accessibility of historical data, as well as the popularity of the search network among residents of Russia, special emphasis is placed on the data of the Yandex search network. It is assumed that tracking the dynamics of requests for the "inflation" and "Central Bank" groups provides operational information everywhere, and for the "exchange rate" and "key rate" groups - in crisis and/or changing economic conditions. The results obtained on the search statistics of the selected keywords were tested as proxy indicators in the framework of forecasting inflation at the level of the Russian Federation based on a set of ARIMAX family models. The results indicate that it is advisable to use keyword statistics as explanatory variables to minimize forecast errors within the framework of inflation forecasting models.

 

Keywords: monetary policy, inflation targeting, inflation expectations, search queries, text analysis, machine learning methods, Yandex

 

JEL: С82; С88; E31; Е52

UDC: 336.7, 338.57

DOI: 10.52342/2587-7666VTE_2025_4_68_90

 

© V. Shcherbakov

© Institute of Economics of the Russian Academy of Sciences «Issues of Theoretical Economics», 2025

 

ЛИТЕРАТУРА

  1. Bank of Russia (2024). Monetary policy guidelines for 2025-2027]. URL: https://cbr.ru/Content/Document/File/164702/on_2025(2026-2027).pdf (access date: 30.06.2024).
  2. Vinokurov S.S., Medved A.A. (2023). Inflation, informational environment and expectations of households. 10.21686/2500-3925-2023-1-37-52.
  3. Goloshchapova I.O., Andreev M.L. (2017). Measuring inflation expectations of the Russian population with the help of machine learning.
  4. Dauit D., Kemalov M., Jaxylykova A. (2020). Overview of the different text summarization methods.
  5. Evstigneeva A. (2023). Communication as a monetary policy tool. URL: https://cbr.ru/StaticHtml/File/146496/research_policy_notes_b_4_1.pdf (access date: 27.01.2025)

complete reference list

close list

  1. Evstigneeva A., Karpov D. (2023). The impact of negative news on the perception of inflation by the population. URL: https://cbr.ru/Content/Document/File/144918/wp_111.pdf (access date: 20.02.2025)
  2. Yerzhan I.S. (2019). Approbation of alternative methods for assessing inflation expectations in Kazakhstan.
  3. Zhemkov M., Kuznetsova O. (2017). Measuring inflation expectations in Russia using stock market data.
  4. Perevyshin Y., Rykalin A. (2018). Modeling Inflation Expectations in the Russian Economy. URL: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3149565 access date: 20.09.2024)
  5. Petrova D.A. (2019). Inflation forecasting based on Internet search queries.
  6. Petrova D. (2022). Assessment of inflation expectations based on Internet data.
  7. Fedyunina A.A., Yurevich M.A., Gorodny N.A. (2024). Pandemic, sanctions and anxiety in Russia’s regions: business expectations nowcasting.
  8. Khazanov A. (2015). On quantification of inflation expectations by the Bank of Russia.
  9. Shulyak E. (2022). Macroeconomic forecasting using data from social media.
  10. Shcherbakov V.S., Kharlamova M.S, Gartvich R.E. (2022). Methods and models for nowcasting economic indicators with help of search queries.
  11. Shcherbakov V.S., Kharlamovs M.S., Yakovina M.Yu. (2022). Search query statistics as a proxy indicator of regional price dynamics.
  12. Yurevich M.A. (2021). Inflation expectations and inflation: nowcasting and forecasting // Journal of Economic Regulation. Vol. 12. No. 2. Pp. 22–35.
  13. Angelico C., Marcucci J., Miccoli M., Quarta F. (2022). Can we measure inflation expectations using Twitter? // Journal of Econometrics. 228. No. 2. Pp. 259–277.
  14. Aromí D., Llada M. (2020). Forecasting inflation with twitter // Asociación Argentina de Economía Política. Working Papers. No. 4308.
  15. Ay B., Ertam F., Fidan G., Aydin G. (2023). Turkish abstractive text document summarization using text to text transfer transformer // Alexandria Engineering Journal. No. 68. Pp. 1-13. https://doi.org/10.1016/j.aej.2023.01.008.
  16. Banbura M., Leiva-Leon D., Menz J-O. (2021). Do Inflation Expectations Improve Model-based Inflation Forecasts? // Banco de Espana Working Paper. No. 2138.
  17. Batchelor R. (2009). How Robust are Quantified Survey Data? Evidence from the United States // Inflation Expectations / Ed. by P. Sinclair. – Pp. 8-33.
  18. Bernanke B. (2007). Inflation Expectations and Inflation Forecasting // Monetary Economics Workshop of the National Bureau of Economic Research Summer Institute / Cambridge, Massachusetts.
  19. Bicchal M., Raja Sethu Durai S. (2019). Rationality of inflation expectations: an interpretation of Google Trends data // Macroeconomics and Finance in Emerging Market Economies. 12. No. 3. Pp. 229–239.
  20. Carlson J.A., Parkin M. (1975). Inflation Expectations // Economica. Vol. 42. No. 166. Pp. 123-138.
  21. Carroll C.D. (2003). Macroeconomic expectations of households and professional forecasters // The Quarterly Journal of economics. Vol. 118. No. 1. Pp. 269–298.
  22. Choi H., Varian H. (2009). Predicting initial claims for unemployment benefits. URL: http://static.googleusercontent.com/media/research.google.com/en/us/archive/papers/initialclaimsUS.pdf (access date: 15.11.2024).
  23. Evstigneeva A., Sidorovskiy M. (2021). Assessment of Clarity of Bank of Russia Monetary Policy Communication by Neural Network Approach // Russian Journal of Money and Finance. Vol. 80. No. 3. Pp. 3–33. DOI: 10.31477/rjmf.202103.03.
  24. Fuhrer J. (2012). The Role of Expectations in Inflation Dynamics // International Journal of Central Banking. No. 8. Pp. 137-165.
  25. Guan B., Zhu X., Yuan Sh. (2024). A T5-based interpretable reading comprehension model with more accurate evidence training // Information Processing & Management. Vol. 61. No. 2. DOI: 10.1016/J.IPM.2023.103584.
  26. Guzman G. (2011). Internet Search Behavior as an Economic Forecasting Tool: The Case of Inflation Expectations // Journal of Economic and Social Measurement. Vol. 36. No. 3. DOI:10.3233/JEM-2011-0342.
  27. Han X., Zhang Zh., Ding N., Gu Y. (2021). Pre-trained models: Past, present, and future // AI Open. No. 2. Pp. 225–250. DOI: 10.1016/J.AIOPEN.2021.08.002.
  28. Hassani H., Silva E.S. (2018). Forecasting UK consumer price inflation using inflation forecasts // Research in Economics. 72. No. 3. Pp. 367–378.
  29. Larsen V. H., Thorsrud L. A., Zhulanova J. (2021). News-driven inflation expectations and information rigidities // Journal of Monetary Economics. No. 117. Pp. 507–520. DOI: 10.1016/j.jmoneco.2020.03.004.
  30. Li X., Shang W., Wang S., Ma J. (2015). A MIDAS modelling framework for Chinese inflation index forecast incorporating Google search data // Electronic Commerce Research and Applications. Vol. 14. No. 2. Pp. 112-125.
  31. Mankiw G., Reis R., Wolfers J. (2003). Disagreement about inflation expectations // NBER Macroeconomic Annual. No. 18. Pp. 209-248.
  32. Niesert R.F., Oorschot J.A, Veldhuisen C.P., Brons K., Lange R-J. (2020). Can Google search data help predict macroeconomic series? // International Journal of Forecasting. Vol. 36. No. 3. Pp. 1163-1172.
  33. Raffel C., Shazeer N., Roberts A., Lee K., Narang S., Matena M., Zhou Y., Li W., Liu P. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer // Journal of Machine Learning Research. No. 21. Pp. 1–67.
  34. Sahu S., Chattopadhyay S. (2020). Epidemiology of inflation expectations and internet search: an analysis for India // Journal of Economic Interaction and Coordination. No. 15. Pp. 649-671.
  35. Seabold S., Coppola A. (2015). Nowcasting Prices Using Google Trends: An Application to Central America // World Bank Policy Research Working Paper. No. 7398. Pp. 1-40.
  36. Shcherbakov V.S., Karpov I.A. (2024). Regional Inflation Analysis Using Social Network Data // Economy of regions. Vol. 20. No. 3. Pp. 930–946. DOI: 10.17059/EKON.REG.2024-3-21
  37. Thrun S., Pratt L. (1998). Learning to learn: Introduction and overview // Springer Science & Business Media.
  38. Vaswani A., Shazeer N.M., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser L., Polosukhin I. (2017). Attention is All you Need // ArXiv, abs/1706.03762.
  39. Wang M., Xie P., Du Y., Hu X. (2023). T5-Based Model for Abstractive Summarization: A Semi-Supervised Learning Approach with Consistency Loss Functions // Applied Sciences. 13. No. 12. Pp. 1-16. DOI: 10.3390/APP13127111-
  40. Wei Y., Zhang X., Wang S. (2017). Can search data help forecast inflation? Evidence from a 13-country panel // 2017 IEEE International Conference on Big Data (Big Data). DOI: 10.1109/BigData.2017.8258442
  41. Yadav D., Desai J., Yadav A.K. (2022). Automatic Text Summarization Methods: A comprehensive Review // arXiv:2204.01849.
  42. Zhang C., Lv B., Peng G., Liu Y., Yuan Q. (2012). A study on correlation between web search data and CPI // In Recent Progress in Data Engineering and Internet Technology. Pp. 269–274.
  43. Zmitrovich D., Abramov A., Kalmykov A., Tikhonova M., Taktasheva E., Astafurov D., Baushenko M., Snegirev A., Shavrina T., Markov S., Mikhailov V., Fenogenova A. (2023). A Family of Pretrained Transformer Language Models for Russian. DOI: 10.48550/arXiv.2309.10931.

 

 

Manuscript submission date  23.06.2025

Manuscript acceptance date: 06.09.2025

 

For citation:

Shcherbakov V.S. Measuring Russian Public Inflation Expectations Using Internet Search Data: A Top-Down Approach // Voprosy teoreticheskoy ekonomiki. 2025. No. 4. Pp. 68–90. DOI: 10.52342/2587-7666VTE_2025_4_68_90.