Forecasting Latin-American Yield Curves: An Artificial Neural Network Approach
La serie Borradores de Economía es una publicación de la Subgerencia de Estudios Económicos del Banco de la República. Los trabajos son de carácter provisional, las opiniones y posibles errores son responsabilidad exclusiva del autor y sus contenidos no comprometen al Banco de la República ni a su Junta Directiva.
This document explores the predictive power of the yield curves in Latin America (Colombia, Mexico, Peru and Chile) taking into account the factors set by the specifications of Nelson & Siegel and Svensson. Several forecasting methodologies are contrasted: an autoregressive model, a vector autoregressive model, artificial neural networks on each individual factor, and artificial neural networks on all factors that explain the yield curve. The out-of-sample performance of the fitting models improves with the neural networks in the one-month-ahead forecast along all studied yield curves. Moreover, the three factor model developed by Nelson & Siegel proves to be the best choice for out-of-sample forecasting. Finally, the success of the cross variable interaction strongly depends on the selected yield curve.
The opinions and statements are the sole responsibility of the author and do not necessarily represent neither those of the Banco de la República nor of its Board of Directors. Any remaining errors are my own.
