Abstract
We propose a novel monetary policy strategy in an attempt to provide an auxiliary tool to central banks, whose main predictive models are still from the Dynamic Stochastic General Equilibrium (DSGE) family, which has some flaws. We derive an objective function from three empirical relationships that have long been established in the economic literature and we seek to minimise the value of this function by choosing the interest rate via a genetic algorithm. Since the function is forward looking, we use a neural network to predict values of unemployment and inflation. Using data from Brazil, simulation results suggest that had the Brazilian central bank applied our strategy, and all other economic conditions remained equal, inflation could have been lower for 62.48% of the time. Predicted unemployment, however, was lower only for 39.69% of covered periods, as it faces a trade-off with inflation.
Supported by Pontifical Catholic University of Rio de Janeiro.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A country’s total production of final goods and services.
- 2.
The word natural refers to the value of a given country’s economic variable when production of goods and services is operating at full capacity, i.e. production would not increase with more resources.
- 3.
From portuguese, Sistema Especial de Liquidação e Custódia, which stands for Special Clearance and Escrow System. It is the base interest rate in Brazil.
- 4.
This family of functions, i.e. \(z = x_1^{a_1} \cdot x_2^{a_2} \cdot ... \cdot x_n^{a_n}\), possesses a number of important properties which have made it widely useful in the analysis of economic theories.
- 5.
We tried several other horizons, but this one delivered the best results.
- 6.
From portuguese, Pesquisa Nacional por Amostra de DomicÃlios ContÃnua, which translates into Continuous National Household Sample Survey.
- 7.
Although real world unemployment and inflation vary weekly, for these variables we dispose only of aggregate data from the end of each month. Therefore, the best approximation for a week of a given month is the value reported for the end of that same month. Some available data is daily and can be used to enhance this approximation through a forecasting model, which is part of what we are doing here.
- 8.
This rate is slightly different from the SELIC, since it is determined by the market.
- 9.
The machine in which we ran the algorithm has the following specifications: processor Intel(R) Core(TM) i7-4700MQ, CPU 2.40Â GHz; memory 16Â gb; operating system Ubuntu 18.04.2 LTS.
References
Akerlof, G.A.: The missing motivation in macroeconomics. Am. Econ. Rev. 97(1), 5–36 (2007)
Ball, L. et al.: Does one law fit all? Cross-country evidence on Okun’s Law. In: documento presentado en el IMF-OCP Workshop on Global Labour Markets, Paris, vol. 1 (2016)
Barnichon, R., Garda, P.: Forecasting unemployment across countries: the ins and outs. Eur. Econ. Rev. 84, 165–183 (2016)
Blanchard, O.: On the future of macroeconomic models. Oxford Rev. Econ. Policy 34(1–2), 43–54 (2018)
Chakraborty, C., Joseph, A.: Machine learning at central banks. Bank of England working papers 674. Bank of England, September 2017
Christiano, L.J., Eichenbaum, M.: Liquidity effects, monetary policy, and the business cycle. J. Money Credit Bank. 27(4), 1113–1136 (1995)
Clarida, R., Gali, J., Gertler, M.: The science of monetary policy: a new Keynesian perspective. J. Econ. Lit. 37(4), 1661–1707 (1999)
Coibion, O., Gorodnichenko, Y., Ulate, M.: Is Inflation just around the corner? The Phillips curve and global inflationary pressures. In: AEA Papers and Proceedings, vol. 109, pp. 465–469 (2019)
Kukal, J., Van Quang, T.: A monetary policy rule based on fuzzy control in an inflation targeting framework. Prague Econ. Pap. 23, 290–314 (2014)
Romer, P.: The trouble with macroeconomics. New York University, Technical report, Stern School of Business (2016)
Röonnqvist, S., Sarlin, P.: Bank distress in the news: describing events through deep learning. Neurocomputing 264, 57–70 (2017)
Stock, J.H., Watson, M.W.: Forecasting inflation. J. Monet. Econ. 44(2), 293–335 (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Speranza, T.F., Tanscheit, R., Vellasco, M.M.B.R. (2020). A Monetary Policy Strategy Based on Genetic Algorithms and Neural Networks. In: Iliadis, L., Angelov, P., Jayne, C., Pimenidis, E. (eds) Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. EANN 2020. Proceedings of the International Neural Networks Society, vol 2. Springer, Cham. https://doi.org/10.1007/978-3-030-48791-1_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-48791-1_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-48790-4
Online ISBN: 978-3-030-48791-1
eBook Packages: Computer ScienceComputer Science (R0)