Template-Type: ReDIF-Article 1.0
Author-Name: Batuhan Koyuncu
Author-Name: Byeungchun Kwon
Author-Name: Marco Jacopo Lombardi
Author-Name: Fernando Perez-Cruz
Author-Name: Hyun Song Shin
Title: BISTRO: a general purpose oracle for macroeconomic time series
Abstract: Predictions of macroeconomic variables are a key input to economic policy, yet traditional econometric approaches have the limitation that the model needs to be tailored to the specific task. The advent of large language models (LLMs) opens up the tantalising prospect that a single general model can tackle a wide variety of tasks. This article introduces the BIS Time-series Regression Oracle (BISTRO), a general purpose time series model for macroeconomic forecasting. Building on the transformer architecture underlying LLMs, BISTRO is fine-tuned on the large repository of macroeconomic data maintained at the BIS. We put the model through its paces by assessing how well it forecasts the 2021 inflation surge. In contrast to standard benchmarks, which mechanically project a reversion to the mean, BISTRO correctly anticipates the persistence of the inflation wave. This highlights its ability to adapt to unfamiliar patterns in the data. Thus, BISTRO holds promise for producing reliable baseline forecasts and for scenario analysis.
Journal: BIS Quarterly Review
File-URL: https://www.bis.org/publ/qtrpdf/r_qt2603d.pdf
File-Format: Application/pdf
File-URL: https://www.bis.org/publ/qtrpdf/r_qt2603d.htm
File-Format: text/html
Year: 2026
Month: March
Classification-JEL: C32, C45, C55, C87
Handle: RePEc:bis:bisqtr:2603d