IDEAS home Printed from https://ideas.repec.org/p/bdr/borrec/1375.html

Experimenting with Large Language Models for Inflation Forecasting in Colombia

Author

Listed:
  • Aarón Levi Garavito-Acosta
  • Wilmer Martinez-Rivera
  • Juan José Ospina-Tejeiro
  • Edgar Caicedo-García

Abstract

This paper develops and applies a standardized framework for forecasting year-on-year inflation in Colombia using large language models (LLMs). We conduct six sequential experiments in which the information set available to the models is progressively expanded by incorporating historical macroeconomic data, contextual indicators, explicit economic structure, and contemporaneous information retrieved through web search. Each configuration is executed daily and generates 24-month inflation forecasts in real time rather than retrospectively, together with qualitative explanations of the forecasts and, in the more advanced configurations, assessments of the shocks affecting inflation. This real-time design mitigates look-ahead bias and produces genuine forecast vintages. The framework is implemented as a programmatic pipeline in Python that queries the OpenAI and Google APIs, executes predefined experiment-specific prompts, and automatically processes and stores the model responses, while applying forecast validation and revision procedures in the more advanced configurations. The results show that richer information environments produce less monotonic inflation paths that remain above the 3% target over the forecast horizon and are more consistent with the contemporaneous domestic and external shocks affecting inflation. The qualitative analysis also enables the identification of key inflation drivers and the interactions among them. These richer forecast paths are broadly consistent with the pattern observed in survey-based inflation expectations. A formal evaluation of forecast accuracy will be conducted as additional real-time forecast vintages become available. *** RESUMEN: Este artículo desarrolla y aplica un marco estandarizado para pronosticar la inflación anual en Colombia utilizando los LLM (Large Language Models LLMs). Se llevan a cabo seis experimentos secuenciales en los que el conjunto de información disponible para los modelos se amplía progresivamente mediante la incorporación de datos macroeconómicos históricos, indicadores contextuales, una estructura económica explícita e información contemporánea obtenida a través de búsquedas en la web. Cada configuración se ejecuta diariamente y genera pronósticos de inflación a 24 meses en tiempo real junto con explicaciones cualitativas de las proyecciones. El marco se implementa mediante un pipeline programático en Python que consulta las API de OpenAI y Google, ejecuta prompts predefinidos y específicos para cada experimento, y procesa y almacena automáticamente las respuestas de los modelos. Los resultados muestran que los entornos con conjuntos de información más ricos generan trayectorias de inflación menos monotónicas, que permanecen por encima de la meta del 3% a lo largo del horizonte de pronóstico y son más consistentes con los choques domésticos y externos contemporáneos que afectan la inflación. El análisis cualitativo también permite identificar los principales determinantes de la inflación y las interacciones entre ellos. Estas trayectorias de pronóstico, construidas a partir de conjuntos de información más amplios, son en términos generales consistentes con el patrón observado en las expectativas de inflación provenientes de encuestas.

Suggested Citation

  • Aarón Levi Garavito-Acosta & Wilmer Martinez-Rivera & Juan José Ospina-Tejeiro & Edgar Caicedo-García, 2026. "Experimenting with Large Language Models for Inflation Forecasting in Colombia," Borradores de Economia 1375, Banco de la Republica de Colombia.
  • Handle: RePEc:bdr:borrec:1375
    as

    Download full text from publisher

    File URL: https://repositorio.banrep.gov.co/bitstream/handle/20.500.12134/11452/be_1375.pdf
    Download Restriction: no
    ---><---

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • C53 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Forecasting and Prediction Models; Simulation Methods
    • E31 - Macroeconomics and Monetary Economics - - Prices, Business Fluctuations, and Cycles - - - Price Level; Inflation; Deflation
    • E37 - Macroeconomics and Monetary Economics - - Prices, Business Fluctuations, and Cycles - - - Forecasting and Simulation: Models and Applications
    • F31 - International Economics - - International Finance - - - Foreign Exchange
    • E23 - Macroeconomics and Monetary Economics - - Consumption, Saving, Production, Employment, and Investment - - - Production

    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:1375. 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.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.