Author
Listed:
- Marlon Salazar
- Andrés Salazar-Mejía
- Jorge Daniel Guevara-Acevedo
- Juan David Duitama-Correa
Abstract
La Tasa de Cambio Real de Equilibrio (ERER, por sus siglas en inglés) es una variable latente comúnmente monitoreada como posible indicador de vulnerabilidades externas, cuya estimación se puede ver afectada por las interacciones no lineales entre los fundamentales subyacentes y por la naturaleza cambiante en el tiempo de su influencia. Este trabajo propone un modelo de redes neuronales (NN-ERER) basado en una arquitectura de Red Neuronal Dirigida por Ramas (BDNN, por sus siglas en inglés) que estima la ERER para Colombia separando los determinantes de largo y corto plazo de la tasa de cambio real (RER). El componente de largo plazo se construye a partir de bloques asociados a términos de intercambio, política fiscal, productividad y deuda externa, mientras que el componente de corto plazo se divide en bloques de variables con efectos positivos y negativos esperados. Las restricciones teóricas de signo se codifican en la arquitectura, restringiendo la estimación mientras se preserva la flexibilidad no lineal. Esta estructura también permite descomponer parcialmente el desalineamiento de la RER en determinantes de corto plazo y residuales no explicados. Los resultados empíricos indican que la contribución relativa de los fundamentales subyacentes a la ERER ha evolucionado en el tiempo, con los términos de intercambio y la deuda externa particularmente relevantes durante el período de altos precios de commodities a mediados de los 2000, y los factores fiscales ganando peso en el período post-COVID-19. Los desalineamientos en 2008–2009 y después de 2021 son atribuibles en gran parte a factores de corto plazo, posiblemente ligados a volatilidad global, incertidumbre, y cambios en los diferenciales de tasas de interés. *** ABSTRACT: The Equilibrium Real Exchange Rate (ERER) is a latent variable commonly monitored as a potential indicator of external vulnerabilities, yet its estimation is challenged by the non-linear interactions among the underlying fundamentals and by the time-varying nature of their influence. This paper proposes a Neural Network Equilibrium Real Exchange Rate (NN-ERER) model based on a Branch Directed Neural Network (BDNN) architecture that estimates the ERER for the Colombian peso by separating long- and short-run determinants of the real exchange rate (RER). The long-run component is constructed from blocks associated with terms of trade, fiscal policy, productivity, and external debt, while the short-run component is divided into blocks of variables with positive and negative expected effects. Theoretical sign restrictions are encoded into the architecture, constraining the estimation while preserving non-linear flexibility. This structure also allows the RER misalignment to be partially decomposed into short-term determinants and unexplained residuals. The empirical results indicate that the relative contribution of the fundamentals underlying the ERER has evolved over time, with terms of trade and external debt particularly relevant during the period of high commodity prices in the mid-2000s, and fiscal factors gaining weight in the post-COVID-19 period. Misalignments in 2008–2009 and after 2021 are largely attributable to short-run factors, plausibly linked to global volatility, uncertainty, and shifts in interest rate differentials.
Suggested Citation
Marlon Salazar & Andrés Salazar-Mejía & Jorge Daniel Guevara-Acevedo & Juan David Duitama-Correa, 2026.
"Tasa de Cambio Real de equilibrio basada en Redes neuronales,"
Borradores de Economia
1361, Banco de la Republica de Colombia.
Handle:
RePEc:bdr:borrec:1361
Download full text from publisher
More about this item
Keywords
;
;
;
;
;
;
JEL classification:
- C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
- F31 - International Economics - - International Finance - - - Foreign Exchange
- F32 - International Economics - - International Finance - - - Current Account Adjustment; Short-term Capital Movements
- F41 - International Economics - - Macroeconomic Aspects of International Trade and Finance - - - Open Economy Macroeconomics
Statistics
Access and download statistics
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:bdr:borrec:1361. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Clorith Angélica Bahos Olivera (email available below). General contact details of provider: https://edirc.repec.org/data/brcgvco.html .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.