Pronóstico de la inflación en tiempos de estabilidad y crisis: un enfoque con Machine Learning
Abstract
La economía boliviana atraviesa su crisis más grave desde la década de 1980, marcada por una drástica transición de una inflación baja y estable a presiones inflacionarias pronunciadas. En este contexto, el desarrollo de herramientas de pronóstico fiables se ha vuelto cada vez más crucial. Este estudio evalúa el rendimiento predictivo de varios modelos de Machine Learning (ML) ampliamente utilizados en dos condiciones macroeconómicas distintas: periodos de relativa estabilidad y periodos de crisis. Los resultados revelan que, en general, los modelos de ML superan a los enfoques econométricos tradicionales en ambas condiciones, siendo el algoritmo XGBoost el que demuestra un rendimiento más destacable. Además, se observó que la incorporación de un conjunto más amplio de indicadores macroeconómicos mejora la precisión del pronóstico. Estos resultados sugieren que las técnicas de ML pueden servir como complementos valiosos para los modelos econométricos en el pronóstico macroeconómico, especialmente en entornos complejos como el de Bolivia.
Abstract** The Bolivian economy is undergoing its most severe crisis since the 1980s, marked by a dramatic transition from low and stable inflation to pronounced inflationary pressures. In this context, the development of reliable forecasting tools has become increasingly critical. This study evaluates the predictive performance of several widely used Machine Learning (ML) models under two distinct macroeconomic conditions: periods of relative stability and periods of crisis. The findings reveal that ML models in general outperform traditional econometric approaches across both conditions, with the XGBoost algorithm demonstrating the best performance. Additionally, it was found that incorporating a broader set of macroeconomic indicators enhances forecast accuracy. These results suggest that ML techniques can serve as valuable complements to econometric models in macroeconomic forecasting, particularly in complex environments such as Bolivia's.
Abstract** The Bolivian economy is undergoing its most severe crisis since the 1980s, marked by a dramatic transition from low and stable inflation to pronounced inflationary pressures. In this context, the development of reliable forecasting tools has become increasingly critical. This study evaluates the predictive performance of several widely used Machine Learning (ML) models under two distinct macroeconomic conditions: periods of relative stability and periods of crisis. The findings reveal that ML models in general outperform traditional econometric approaches across both conditions, with the XGBoost algorithm demonstrating the best performance. Additionally, it was found that incorporating a broader set of macroeconomic indicators enhances forecast accuracy. These results suggest that ML techniques can serve as valuable complements to econometric models in macroeconomic forecasting, particularly in complex environments such as Bolivia's.
Description
No. 44