Your browser does not support the PubReader view.
Go to this page to see a list of supporting browsers.
Seoul Journal of Economics
[ Article ]
Seoul Journal of Economics - Vol. 37, No. 4, pp.243-271
ISSN: 1225-0279 (Print)
Print publication date 30 Nov 2024
Received 27 May 2024 Revised 16 Sep 2024 Accepted 10 Oct 2024
DOI: https://doi.org/10.22904/sje.2024.37.4.003

Inflation Forecasting - Are ML Models Superior? Evidence from India

Sudipta Dutta
Sudipta Dutta: Reserve Bank of India, Mumbai-400051, Maharashtra, India, Tel: 022-26578345 sudipta.dutta.stat@gmail.comsudiptadutta@rbi.org.in

JEL Classification: C53, E58

Abstract

Disruptions in the channels of production, distribution and sale of agricultural and industrial products driven by the pandemic outbreak affected the linkages of inflation across the world as well as the accuracy of traditional inflation forecasting models. The validity of linear econometric models, which assume a linear and static linakge between the variable of interest and its regressors, have long been a subject of scrutiny. As a result, alternative models, especially, machine learning (ML) based predictive models have emerged in an attempt to more accurately capture the evolving dynamics of inflation. ML models have the capability to capture non-linear connections between inflation and its determinants. The study compares the forecasting performance of various ML models with popular econometric models for both the period prior to the pandemic as well as the period post the pandemic. The findings substantiate the superiority of ML models over linear econometric models in terms of improved predictive performance when forecasting inflation in India over various horizons.

Keywords:

Inflation, Econometric, Machine learning, Neural network, Long-short term memory

Acknowledgments

The comments received from the Editor and an anonymous reviewer are gratefully acknowledged. The views and opinions expressed in this paper are solely of the author and does not necessarily reflect the views of the author’s institution.

References

  • Almosova, A. and Andresen, N., Non-linear inflation forecasting with recurrent neural networks, Technical Report, European Central Bank (ECB), 2019.
  • Arrieta, A. B., Rodriguez, N. D., Ser, J. D., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Lopez, S. G., Molina, D., Benjamins, R., Chatila, R. and Herrera, F., “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.” Information Fusion 58(2020): 82-115. [https://doi.org/10.1016/j.inffus.2019.12.012]
  • Blagrave, P. and Lian, W., India’s Inflation Process Before and After Flexible Inflation Targeting, IMF Working Paper, WP/20/251, 2020. [https://doi.org/10.5089/9781513561233.001]
  • Barkan, O., Benchimol, J., Caspi, I., Cohen, E., Hammer, A. and Koenigstein, A., “Forecasting CPI Inflation Components with Hierarchical Recurrent Neural Networks.” International Journal of Forecasting 39(No. 3 2023): 1145-1162. [https://doi.org/10.1016/j.ijforecast.2022.04.009]
  • Binner, J. M., Bissoondeeal, R. K, Elger, T., Gazely, A. M. and Mullineux, A. W., “A comparison of linear forecasting models and neural networks: an application to Euro inflation and Euro Divisia.” Applied Economics 37(No. 6 2005): 665-680. [https://doi.org/10.1080/0003684052000343679]
  • Bobeica, E. and Hartwig, B., The COVID-19 Shock and Challenges for Time Series Models, ECB Working Paper Series, No. 2558, 2021. [https://doi.org/10.2139/ssrn.3854294]
  • Chakraborty, C. and Joseph, A., Machine Learning at Central Banks, Bank of England Staff Working Paper No. 674, 2017. [https://doi.org/10.2139/ssrn.3031796]
  • Collins, C., Forbes, K. and Gagnon, J., Pandemic Inflation and Nonlinear, Global Phillips Curves, CEPR VOXEU Column, https://cepr. org/voxeu/columns/pandemic-inflation-and-nonlinear-global-phillips-curves, 2021.
  • Doerr, S., Gambacorta, L. and Serena, J. M., Big Data and Machine Learning in Central Banking, BIS Working Papers No. 930, Bank for International Settlements, 2021.
  • Dua, P. and Goel, D., “Determinants of Inflation in India.” The Journal of Developing Areas 55(No. 2 2021): 205-221. [https://doi.org/10.1353/jda.2021.0040]
  • Fourati, H., Maaloul, R. and Fourati, L. C., “A Survey of 5G Network Systems: Challenges and Machine Learning Approaches.” International Journal of Machine Learning and Cybernetics 12(2021): 385-431. [https://doi.org/10.1007/s13042-020-01178-4]
  • Fulton, C. and Kirstin, H., Forecasting US inflation in real time, Finance and Economics Discussion Series 2021-014, Board of Governors of the Federal Reserve System, Washington DC, 2021. [https://doi.org/10.17016/feds.2021.014]
  • Giacomini, R. and White, H., “Tests of Conditional Predictive Ability.” Econometrica 74(No. 6 2006): 1545–1578. [https://doi.org/10.1111/j.1468-0262.2006.00718.x]
  • International Monetary Fund, Quarterly National Accounts Manual, Chapter 7 - Seasonal Adjustment, 2017.
  • John, J., Singh, S. and Kapur, M., Inflation Forecast Combinations - The Indian Experience, Reserve Bank of India Working Paper Series (DEPR) No. 11, 2020.
  • Jose, J., Shekhar, H., Kundu, S., Kishore, V., and Bhoi, B. B., “Alternative Inflation Forecasting Models for India – What Performs Better in Practice?.” Reserve Bank of India Occasional Papers 42(No. 1 2021): 71-121.
  • Kar, S., Bashir, A. and Jain, M., New Approaches to Forecasting Growth and Inflation: Big Data and Machine Learning, Institute of Economic Growth, Working Papers No. 446, 2021.
  • Mahajan, K. and Srinivasan, A., “Inflation Forecasting in Emerging Markets: A Machine Learning Approach.” CAFRAL research publications, Centre for Advanced Financial Research and Learning (CAFRAL), 2020. https://www.cafral.org.in/sfControl/content/Speech/221202090803PMMahajan_Srinivasan_2019.pdf
  • McNelis, P. and McAdam, P., Forecasting inflation with thick models and neural networks, European Central Bank Working Paper Series No. 352, 2004. [https://doi.org/10.2139/ssrn.533014]
  • Mohanty, D. and John, J., “Determinants of Inflation in India.” Journal of Asian Economics 36(2015): 86-96. [https://doi.org/10.1016/j.asieco.2014.08.002]
  • Nakamura, E., “Inflation forecasting using a neural network.” Economics Letters 86(No. 3 2005): 373–378. [https://doi.org/10.1016/j.econlet.2004.09.003]
  • Paranhos, L., Predicting Inflation with Neural Networks, Warwick Economics Research Paper Series No. 1344, University of Warwick, Department of Economics, 2021.
  • Patra, M. D., Khundrakpam, J. K. and George, A. T., Post-Global Crisis Inflation Dynamics in India, What has Changed?, India Policy Forum 10(No. 1 2014): 117-203.
  • Pratap, B. and Sengupta, S., Macroeconomic Forecasting in India: Does Machine L earning H old the Key to Better F orecasts?, Reserve Bank of India Working Paper Series WPS (DEPR) No. 4, 2019. [https://doi.org/10.2139/ssrn.3852945]
  • Rani, S. J., Haragopal, V. V. and Reddy, M. K., “Forecasting inflation rate of India using neural networks.” International Journal of Computer Applications 158(No. 5 2017): 45–48. [https://doi.org/10.5120/ijca2017912866]
  • Reserve Bank of India, Report of the Expert Committee to Revise and Strengthen the Monetary Policy Framework, Mumbai: Reserve Bank of India, 2014.
  • Reserve Bank of India, Report on Currency and Finance 2020-21, 2021.
  • Rodríguez-Vargas, A., “Forecasting Costa Rican inflation with Machine Learning methods.” Latin American Journal of Central Banking 1(No. 1-4 2020). [https://doi.org/10.1016/j.latcb.2020.100012]
  • Singh, N., “Inflation Forecasting in India: Are Machine Learning Techniques Useful?.” Reserve Bank of India Occasional Papers 43(No. 2 2022).
  • Svensson, L. E. O., “Inflation Targeting as a Monetary Policy Rule.” Journal of Monetary Economics 43(No. 3 1999): 607-654. [https://doi.org/10.1016/S0304-3932(99)00007-0]
  • Swanson, N. R. and White, H., “A Model Selection Approach to Real- Time Macroeconomic Forecasting Using Linear Models and Artificial Neural Networks.” The Review of Economics and Statistics 79(No. 4 1997): 540–550. [https://doi.org/10.1162/003465397557123]
  • Theoharidis, A. F., Forecasting Inflation Using Deep Learning: An Application of Convolutional LSTM Networks and Variational Autoencoders, Insper Institute of Education and Research, São Paulo, Brazil, 2021.
  • Varian, H. R., “Big Data: New Tricks for Econometrics.” Journal of Economic Perspectives 28 (No. 2 2014): 3–28. [https://doi.org/10.1257/jep.28.2.3]