Template-Type: ReDIF-Paper 1.0
Author-Name: Batuhan Koyuncu
Author-X-Name-First: Batuhan
Author-X-Name-Last: Koyuncu
Author-Name: Byeungchun Kwon
Author-X-Name-First: Byeungchun
Author-X-Name-Last: Kwon
Author-Name: Marco Jacopo Lombardi
Author-X-Name-First: Marco Jacopo
Author-X-Name-Last: Lombardi
Author-Name: Fernando Perez-Cruz
Author-X-Name-First: Fernando
Author-X-Name-Last: Perez-Cruz
Author-Name: Hyun Song Shin
Author-X-Name-First: Hyun Song
Author-X-Name-Last: Shin
Title: Introducing BISTRO: a foundational model for unconditional and conditional forecasting of macroeconomic time series
Abstract: This article introduces the BIS Time-series Regression Oracle (BISTRO), a general purpose time series model for macroeconomic forecasting. Its edge over traditional econometric approaches lies in its ability to deal with generic unconditional and conditional forecasting tasks, without requiring to adjust the model to the macroe conomic tasks being tackled. Building on the transformer architecture underlying LLMs, BISTRO is fine-tuned on the large repository of macroeconomic data main tained at the BIS. We show that BISTRO provides reliable unconditional forecasts for key macroeconomic aggregates and illustrate how using it for conditional fore casting can help unveiling patterns of nonlinearity in the data.
Creation-Date: 2026-03
File-URL: https://www.bis.org/publ/work1337.pdf
File-Format: Application/pdf
File-Function: Full PDF document
File-URL: https://www.bis.org/publ/work1337.htm
File-Format: text/html
Number: 1337
Keywords: forecasting, scenarios, large language models
Classification-JEL: C32, C45, C55, C87
Handle: RePEc:bis:biswps:1337