Skip to main content
Top

2023 | OriginalPaper | Chapter

22. Machine Learning in Macroeconomics: Application to DSGE Models

Authors : D. M. Nachane, Aditi Chaubal

Published in: India’s Contemporary Macroeconomic Themes

Publisher: Springer Nature Singapore

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Machine learning—a tool primarily belonging to the statistical, physical, and technological streams—has found its way into the economic sciences too. This paper attempts to conduct a brief review of literature with respect to some of the machine learning tools being used in macroeconomic forecasting, in particular, in DSGE models. The DSGE models have found widespread applicability owing to their firm theoretical micro-foundations in the Real Business Cycle school. Despite their practicality and applicability, these models drew criticism following the global financial crisis broadly due to structural drawbacks of (i) actual economic agents rarely exhibit rational expectations (ii) structure of markets rarely following the efficient market hypothesis, and (iii) aggregation of the behavior of the representative agent to derive macro-processes being true only under restrictive assumptions. This was further augmented by econometric issues of overfitting, simplifying yet false and non-testable identification restrictions, structural (and not practical) specification of the model, etc. The machine learning techniques are applied to attain the objective of reducing dimensionality, and better predictive performance. We then exposit the detailed specifications of two machine learning techniques utilized in studies which implemented the DSGE using machine learning tools, viz., random forests and support vector machines (SVMs), which are used in the classification of the data used in DSGE models. The machine learning techniques applied to classify the data in a DSGE model across studies include the random forests, SVMs, neural networks, logistic regressions, etc. The paper concludes with the implications that the introduction of the machine learning techniques has on DSGE models, and the policy implications thereof.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Footnotes
1
The inputs and outputs can be vectors, data, images, documents, etc.
 
2
See James et al. (2013), pp. 226–240 for a detailed description of ridge and LASSO regressions.
 
3
Note that both these techniques can also be used to analyze classification problems in forecasting as has been done for DSGE models.
 
4
However, the components or building blocks constituting the model may perform poorly in terms of forecasting ability and are known as weak learners.
 
5
Classification trees are used to predict qualitative responses unlike regression trees in which the response is quantitative. In this case, the prediction for each observation is obtaining the most commonly occurring class of training observations in the region that the observation belongs to (where the classes are based on the characteristics of the observations). The focus of classification trees is thus to predict the class to which each observation belongs.
 
6
Following convention of James et al. (2021).
 
7
Trees have high variance which is reduced by bagging but the individual trees are highly correlated.
 
8
The steps are given for regression trees but also apply to classification trees.
 
9
The thumb rule is that p is \(\sqrt{n}\) for classification trees, and [n/3] for regression trees.
 
10
Note the term classification is used here (and in other parts of the paper) in two contexts—the former to signify the methodology of the tool and the latter to signify the types of problems the tool can help analyze.
 
11
A detailed account of the concepts of hyperplanes, maximal margin or support vector classifier, and support vectors is given in James et al. (2021), pp. 367–378.
 
12
(James et al. (2021)): Kernel is a function that quantifies the similarity of two observations using either linear inner product (resulting in the SVC) or a polynomial function (of degree d) which results in a nonlinear hyperplane.
 
13
Note the datasets xi and yi are given in vector notations as X and y, respectively.
 
14
The value of the loss function is small for the observations that are farther from the decision boundary or separating hyperplane.
 
15
In the case of fiscal dominance regime, the price level is not under the control of the monetary authority, whereas the opposite is true in the case of a monetary dominance regime.
 
Literature
go back to reference Carbonell, J., Michalski, R. and Mitchell, T. (1983). An overview of machine learning, In Michalski, R., Carbonell, J. and Mitchell, T. (eds.) Machine Learning – An Artificial Intelligence approach, pp. 3–23, TIOGA Publishing Co.:USA. Carbonell, J., Michalski, R. and Mitchell, T. (1983). An overview of machine learning, In Michalski, R., Carbonell, J. and Mitchell, T. (eds.) Machine Learning – An Artificial Intelligence approach, pp. 3–23, TIOGA Publishing Co.:USA.
go back to reference Christiano, L. J., & Eichenbaum, M. (1992). Current real business cycle theories and aggregate labour market fluctuations. American Economic Review, 82, 430–450. Christiano, L. J., & Eichenbaum, M. (1992). Current real business cycle theories and aggregate labour market fluctuations. American Economic Review, 82, 430–450.
go back to reference Coulombe, P., Leroux, M., & Stevanovic, D. (2022). How is machine learning useful for macroeconomic forecasting? Journal of Applied Econometrics, 37(5), 920–964.CrossRef Coulombe, P., Leroux, M., & Stevanovic, D. (2022). How is machine learning useful for macroeconomic forecasting? Journal of Applied Econometrics, 37(5), 920–964.CrossRef
go back to reference Fève, P., Matheron, J., & Sahuc, J.-G. (2010). Disinflation Shocks in the Eurozone: A DSGE Perspective. Journal of Money, Credit and Banking, 42(2–3), 289–323.CrossRef Fève, P., Matheron, J., & Sahuc, J.-G. (2010). Disinflation Shocks in the Eurozone: A DSGE Perspective. Journal of Money, Credit and Banking, 42(2–3), 289–323.CrossRef
go back to reference Goyal, A. and Kumar, A. (2020). A DSGE model-based analysis of the Indian slowdown, Journal of International Commerce, Economics and Policy, Vol. 11, No. 01. Goyal, A. and Kumar, A. (2020). A DSGE model-based analysis of the Indian slowdown, Journal of International Commerce, Economics and Policy, Vol. 11, No. 01.
go back to reference Guimares, R. (2021). Deep learning macroeconomics [Doctoral thesis, Universidade Federal do Rio Grande do Sul], Federal University of Rio Grande do Sul. Guimares, R. (2021). Deep learning macroeconomics [Doctoral thesis, Universidade Federal do Rio Grande do Sul], Federal University of Rio Grande do Sul.
go back to reference Hall, A. (2018). Machine learning approaches to macroeconomic forecasting, Federal Reserve Bank of Kansas City, Economic Review, Federal Reserve Bank of Kansas City, Issue Q IV, pp. 63–81. Hall, A. (2018). Machine learning approaches to macroeconomic forecasting, Federal Reserve Bank of Kansas City, Economic Review, Federal Reserve Bank of Kansas City, Issue Q IV, pp. 63–81.
go back to reference Hastie, T., Tibshirani, R., Friedman, J. (2008). The elements of statistical learning: Data mining, inference, and prediction, Springer Series in Statistics, 2nd Ed., Springer Science+Business Media, LLC, Springer Nature: New York, USA. Hastie, T., Tibshirani, R., Friedman, J. (2008). The elements of statistical learning: Data mining, inference, and prediction, Springer Series in Statistics, 2nd Ed., Springer Science+Business Media, LLC, Springer Nature: New York, USA.
go back to reference Hinterlang, N. and Hollmayr, J. (2020). Classification of monetary and fiscal dominance regimes using machine learning techniques, Journal of Macroeconomics, Vol. 74, 103469. Hinterlang, N. and Hollmayr, J. (2020). Classification of monetary and fiscal dominance regimes using machine learning techniques, Journal of Macroeconomics, Vol. 74, 103469.
go back to reference Ireland, P. N. (2004). A Method for Taking Models to the Data. Journal of Economic Dynamics & Control, 28, 1205–1226.CrossRef Ireland, P. N. (2004). A Method for Taking Models to the Data. Journal of Economic Dynamics & Control, 28, 1205–1226.CrossRef
go back to reference James, G., Witten, D., Hastie, T., Tibshirani, R. (2021). An Introduction to Statistical Learning with Applications in R, Springer Texts in Statistics, 2nd Ed., Springer Science+Business Media, LLC, Springer Nature: New York, USA. James, G., Witten, D., Hastie, T., Tibshirani, R. (2021). An Introduction to Statistical Learning with Applications in R, Springer Texts in Statistics, 2nd Ed., Springer Science+Business Media, LLC, Springer Nature: New York, USA.
go back to reference Jordan, M., & Mitchell, T. (2015). Machine Learning – Trends, perspectives and prospects. Science, 349(6245), 255–260.CrossRef Jordan, M., & Mitchell, T. (2015). Machine Learning – Trends, perspectives and prospects. Science, 349(6245), 255–260.CrossRef
go back to reference Kar, S., Bashir, A., & Jain, M. (2022). Do Machine Learning Techniques Provide Better Macroeconomic Forecasts?, Economic and Political Weekly, Vol. 57. Issue No., 34, 34–41. Kar, S., Bashir, A., & Jain, M. (2022). Do Machine Learning Techniques Provide Better Macroeconomic Forecasts?, Economic and Political Weekly, Vol. 57. Issue No., 34, 34–41.
go back to reference Kuan, C. M., & White, H. (1994). Artificial neural networks: An econometric perspective. Econometric Reviews, 13(1), 1–91.CrossRef Kuan, C. M., & White, H. (1994). Artificial neural networks: An econometric perspective. Econometric Reviews, 13(1), 1–91.CrossRef
go back to reference Lee, T. H., White, H., & Granger, C. W. J. (1993). Testing for neglected nonlinearity in time series models – A comparison of neural network methods and alternative tests. Journal of Econometrics, 56(3), 269–290.CrossRef Lee, T. H., White, H., & Granger, C. W. J. (1993). Testing for neglected nonlinearity in time series models – A comparison of neural network methods and alternative tests. Journal of Econometrics, 56(3), 269–290.CrossRef
go back to reference Litsios, I., Pilbeam, K., & Asteriou, D. (2021). DSGE modelling for the UK economy 1974–2017. Bulletin of Economic Research, 73(2), 295–323.CrossRef Litsios, I., Pilbeam, K., & Asteriou, D. (2021). DSGE modelling for the UK economy 1974–2017. Bulletin of Economic Research, 73(2), 295–323.CrossRef
go back to reference Medeiros, M. C., Vasconcelos, G. F., Veiga, Á., and Zilberman, E. (2019). Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods, Journal of Business and Economic Statistics, Vol. 0 (0), pp. 1–45. Medeiros, M. C., Vasconcelos, G. F., Veiga, Á., and Zilberman, E. (2019). Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods, Journal of Business and Economic Statistics, Vol. 0 (0), pp. 1–45.
go back to reference Medeiros, M., Terasvirta, T., & Rech, G. (2006). Building neural network models for time series: A statistical approach. Journal of Forecasting, 25, 49–75.CrossRef Medeiros, M., Terasvirta, T., & Rech, G. (2006). Building neural network models for time series: A statistical approach. Journal of Forecasting, 25, 49–75.CrossRef
go back to reference Mitchell, T. (1997): Machine Learning, 1st Ed., McGraw Hill Education, USA. Mitchell, T. (1997): Machine Learning, 1st Ed., McGraw Hill Education, USA. 
go back to reference Nachane, D.M. (2018). Critique of the new consensus macroeconomics and implications for India, India Studies in Business and Economics, Springer, New Delhi. Nachane, D.M. (2018). Critique of the new consensus macroeconomics and implications for India, India Studies in Business and Economics, Springer, New Delhi.
go back to reference Nachane, D. M. (2016). Dynamic Stochastic General Equilibrium Modelling: A Sisyphean Toil? Economic and Political Weekly, 51(12), 68–77. Nachane, D. M. (2016). Dynamic Stochastic General Equilibrium Modelling: A Sisyphean Toil? Economic and Political Weekly, 51(12), 68–77.
go back to reference Nachane, D. M. (2017). Dynamic stochastic general equilibrium (DSGE) modelling in practice: Identification, estimation and evaluation. Macroeconomics and Finance in Emerging Market Economies, 10(2), 107–134.CrossRef Nachane, D. M. (2017). Dynamic stochastic general equilibrium (DSGE) modelling in practice: Identification, estimation and evaluation. Macroeconomics and Finance in Emerging Market Economies, 10(2), 107–134.CrossRef
go back to reference Stempel, D. and Zahner, J. (2022). DSGE models and machine learning: an application to monetary policy in the Euro Area, MAGKS Joint Discussion Paper Series in Economics, No. 32–2022, Philipps-University Marburg, School of Business and Economics, Marburg. Stempel, D. and Zahner, J. (2022). DSGE models and machine learning: an application to monetary policy in the Euro Area, MAGKS Joint Discussion Paper Series in Economics, No. 32–2022, Philipps-University Marburg, School of Business and Economics, Marburg.
go back to reference Stock, J. H. and Watson, M. W. (1999). A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series, In Engle, R. F. and White, H., editors, Cointegration, Causality and Forecasting: A Festschrift for Clive W.J. Granger, pp. 1–44, Oxford University Press: Oxford. Stock, J. H. and Watson, M. W. (1999). A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series, In Engle, R. F. and White, H., editors, Cointegration, Causality and Forecasting: A Festschrift for Clive W.J. Granger, pp. 1–44, Oxford University Press: Oxford.
go back to reference Swanson, N., & White, H. (1997). A model selection approach to real-time macroeconomic forecasting using linear models and artificial neural networks. The Review of Economics and Statistics, 79(4), 540–550.CrossRef Swanson, N., & White, H. (1997). A model selection approach to real-time macroeconomic forecasting using linear models and artificial neural networks. The Review of Economics and Statistics, 79(4), 540–550.CrossRef
go back to reference Zhou, Z. (2021). Machine Learning (S. Liu, Trans.), Springer Nature: Singapore (Original work published 2016). Zhou, Z. (2021). Machine Learning (S. Liu, Trans.), Springer Nature: Singapore (Original work published 2016).
Metadata
Title
Machine Learning in Macroeconomics: Application to DSGE Models
Authors
D. M. Nachane
Aditi Chaubal
Copyright Year
2023
Publisher
Springer Nature Singapore
DOI
https://doi.org/10.1007/978-981-99-5728-6_22