Skip to main content

Banrep paper proposes LLM-driven forecast method

Sequential design enables economists to study ‘information environment’

Central Bank of Colombia, Bogota
The Central Bank of Colombia

Economists at the Central Bank of Colombia (Banrep) have developed a method of forecasting inflation using large language models (LLMs).

Their findings, published in a working paper on October 16, emphasise how the “information environment” shapes the forecast process.

The team used a sequence of six progressively more detailed sets of contextual information to see how forecasts evolved as models were fed additional facts about the economic environment. The researchers used OpenAI’s model GPT-4o

Solo los usuarios que tengan una suscripción de pago o formen parte de una suscripción corporativa pueden imprimir o copiar contenido.

Para acceder a estas opciones, junto con todas las demás ventajas de la suscripción, póngase en contacto con info@centralbanking.com o consulte nuestras opciones de suscripción aquí: subscriptions.centralbanking.com/subscribe

Actualmente no puede copiar este contenido. Póngase en contacto con info@centralbanking.com para obtener más información.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to Central Banking? View our subscription options

Artículos más leídos cargando...

You need to sign in to use this feature. If you don’t have a Central Banking account, please register for a trial.

Iniciar sesión
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account

.